what is literature review in concept paper

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, generate accurate citations for free.

• Knowledge Base

Methodology

• How to Write a Literature Review | Guide, Examples, & Templates

How to Write a Literature Review | Guide, Examples, & Templates

Published on January 2, 2023 by Shona McCombes . Revised on September 11, 2023.

What is a literature review? A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research that you can later apply to your paper, thesis, or dissertation topic .

There are five key steps to writing a literature review:

• Search for relevant literature
• Evaluate sources
• Identify themes, debates, and gaps
• Outline the structure
• Write your literature review

A good literature review doesn’t just summarize sources—it analyzes, synthesizes , and critically evaluates to give a clear picture of the state of knowledge on the subject.

Table of contents

What is the purpose of a literature review, examples of literature reviews, step 1 – search for relevant literature, step 2 – evaluate and select sources, step 3 – identify themes, debates, and gaps, step 4 – outline your literature review’s structure, step 5 – write your literature review, free lecture slides, other interesting articles, frequently asked questions, introduction.

• Quick Run-through
• Step 1 & 2

When you write a thesis , dissertation , or research paper , you will likely have to conduct a literature review to situate your research within existing knowledge. The literature review gives you a chance to:

• Demonstrate your familiarity with the topic and its scholarly context
• Develop a theoretical framework and methodology for your research
• Position your work in relation to other researchers and theorists
• Show how your research addresses a gap or contributes to a debate
• Evaluate the current state of research and demonstrate your knowledge of the scholarly debates around your topic.

Writing literature reviews is a particularly important skill if you want to apply for graduate school or pursue a career in research. We’ve written a step-by-step guide that you can follow below.

A faster, more affordable way to improve your paper

Scribbr’s new AI Proofreader checks your document and corrects spelling, grammar, and punctuation mistakes with near-human accuracy and the efficiency of AI!

Proofread my paper

Writing literature reviews can be quite challenging! A good starting point could be to look at some examples, depending on what kind of literature review you’d like to write.

• Example literature review #1: “Why Do People Migrate? A Review of the Theoretical Literature” ( Theoretical literature review about the development of economic migration theory from the 1950s to today.)
• Example literature review #2: “Literature review as a research methodology: An overview and guidelines” ( Methodological literature review about interdisciplinary knowledge acquisition and production.)
• Example literature review #3: “The Use of Technology in English Language Learning: A Literature Review” ( Thematic literature review about the effects of technology on language acquisition.)
• Example literature review #4: “Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review” ( Chronological literature review about how the concept of listening skills has changed over time.)

You can also check out our templates with literature review examples and sample outlines at the links below.

Download Word doc Download Google doc

Before you begin searching for literature, you need a clearly defined topic .

If you are writing the literature review section of a dissertation or research paper, you will search for literature related to your research problem and questions .

Make a list of keywords

Start by creating a list of keywords related to your research question. Include each of the key concepts or variables you’re interested in, and list any synonyms and related terms. You can add to this list as you discover new keywords in the process of your literature search.

• Social media, Facebook, Instagram, Twitter, Snapchat, TikTok
• Body image, self-perception, self-esteem, mental health
• Generation Z, teenagers, adolescents, youth

Search for relevant sources

Use your keywords to begin searching for sources. Some useful databases to search for journals and articles include:

• Your university’s library catalogue
• Google Scholar
• Project Muse (humanities and social sciences)
• Medline (life sciences and biomedicine)
• EconLit (economics)
• Inspec (physics, engineering and computer science)

You can also use boolean operators to help narrow down your search.

Make sure to read the abstract to find out whether an article is relevant to your question. When you find a useful book or article, you can check the bibliography to find other relevant sources.

You likely won’t be able to read absolutely everything that has been written on your topic, so it will be necessary to evaluate which sources are most relevant to your research question.

For each publication, ask yourself:

• What question or problem is the author addressing?
• What are the key concepts and how are they defined?
• What are the key theories, models, and methods?
• Does the research use established frameworks or take an innovative approach?
• What are the results and conclusions of the study?
• How does the publication relate to other literature in the field? Does it confirm, add to, or challenge established knowledge?
• What are the strengths and weaknesses of the research?

Make sure the sources you use are credible , and make sure you read any landmark studies and major theories in your field of research.

You can use our template to summarize and evaluate sources you’re thinking about using. Click on either button below to download.

Take notes and cite your sources

As you read, you should also begin the writing process. Take notes that you can later incorporate into the text of your literature review.

It is important to keep track of your sources with citations to avoid plagiarism . It can be helpful to make an annotated bibliography , where you compile full citation information and write a paragraph of summary and analysis for each source. This helps you remember what you read and saves time later in the process.

To begin organizing your literature review’s argument and structure, be sure you understand the connections and relationships between the sources you’ve read. Based on your reading and notes, you can look for:

• Trends and patterns (in theory, method or results): do certain approaches become more or less popular over time?
• Themes: what questions or concepts recur across the literature?
• Debates, conflicts and contradictions: where do sources disagree?
• Pivotal publications: are there any influential theories or studies that changed the direction of the field?
• Gaps: what is missing from the literature? Are there weaknesses that need to be addressed?

This step will help you work out the structure of your literature review and (if applicable) show how your own research will contribute to existing knowledge.

• Most research has focused on young women.
• There is an increasing interest in the visual aspects of social media.
• But there is still a lack of robust research on highly visual platforms like Instagram and Snapchat—this is a gap that you could address in your own research.

There are various approaches to organizing the body of a literature review. Depending on the length of your literature review, you can combine several of these strategies (for example, your overall structure might be thematic, but each theme is discussed chronologically).

Chronological

The simplest approach is to trace the development of the topic over time. However, if you choose this strategy, be careful to avoid simply listing and summarizing sources in order.

Try to analyze patterns, turning points and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred.

If you have found some recurring central themes, you can organize your literature review into subsections that address different aspects of the topic.

For example, if you are reviewing literature about inequalities in migrant health outcomes, key themes might include healthcare policy, language barriers, cultural attitudes, legal status, and economic access.

Methodological

If you draw your sources from different disciplines or fields that use a variety of research methods , you might want to compare the results and conclusions that emerge from different approaches. For example:

• Look at what results have emerged in qualitative versus quantitative research
• Discuss how the topic has been approached by empirical versus theoretical scholarship
• Divide the literature into sociological, historical, and cultural sources

Theoretical

A literature review is often the foundation for a theoretical framework . You can use it to discuss various theories, models, and definitions of key concepts.

You might argue for the relevance of a specific theoretical approach, or combine various theoretical concepts to create a framework for your research.

Like any other academic text , your literature review should have an introduction , a main body, and a conclusion . What you include in each depends on the objective of your literature review.

The introduction should clearly establish the focus and purpose of the literature review.

Depending on the length of your literature review, you might want to divide the body into subsections. You can use a subheading for each theme, time period, or methodological approach.

As you write, you can follow these tips:

• Summarize and synthesize: give an overview of the main points of each source and combine them into a coherent whole
• Analyze and interpret: don’t just paraphrase other researchers — add your own interpretations where possible, discussing the significance of findings in relation to the literature as a whole
• Critically evaluate: mention the strengths and weaknesses of your sources
• Write in well-structured paragraphs: use transition words and topic sentences to draw connections, comparisons and contrasts

In the conclusion, you should summarize the key findings you have taken from the literature and emphasize their significance.

When you’ve finished writing and revising your literature review, don’t forget to proofread thoroughly before submitting. Not a language expert? Check out Scribbr’s professional proofreading services !

This article has been adapted into lecture slides that you can use to teach your students about writing a literature review.

Scribbr slides are free to use, customize, and distribute for educational purposes.

Open Google Slides Download PowerPoint

If you want to know more about the research process , methodology , research bias , or statistics , make sure to check out some of our other articles with explanations and examples.

• Sampling methods
• Simple random sampling
• Stratified sampling
• Cluster sampling
• Likert scales
• Reproducibility

 Statistics

• Null hypothesis
• Statistical power
• Probability distribution
• Effect size
• Poisson distribution

Research bias

• Optimism bias
• Cognitive bias
• Implicit bias
• Hawthorne effect
• Anchoring bias
• Explicit bias

A literature review is a survey of scholarly sources (such as books, journal articles, and theses) related to a specific topic or research question .

It is often written as part of a thesis, dissertation , or research paper , in order to situate your work in relation to existing knowledge.

There are several reasons to conduct a literature review at the beginning of a research project:

• To familiarize yourself with the current state of knowledge on your topic
• To ensure that you’re not just repeating what others have already done
• To identify gaps in knowledge and unresolved problems that your research can address
• To develop your theoretical framework and methodology
• To provide an overview of the key findings and debates on the topic

Writing the literature review shows your reader how your work relates to existing research and what new insights it will contribute.

The literature review usually comes near the beginning of your thesis or dissertation . After the introduction , it grounds your research in a scholarly field and leads directly to your theoretical framework or methodology .

A literature review is a survey of credible sources on a topic, often used in dissertations , theses, and research papers . Literature reviews give an overview of knowledge on a subject, helping you identify relevant theories and methods, as well as gaps in existing research. Literature reviews are set up similarly to other  academic texts , with an introduction , a main body, and a conclusion .

An  annotated bibliography is a list of  source references that has a short description (called an annotation ) for each of the sources. It is often assigned as part of the research process for a  paper .  

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the “Cite this Scribbr article” button to automatically add the citation to our free Citation Generator.

McCombes, S. (2023, September 11). How to Write a Literature Review | Guide, Examples, & Templates. Scribbr. Retrieved November 14, 2023, from https://www.scribbr.com/dissertation/literature-review/

Is this article helpful?

Shona McCombes

Other students also liked, what is a theoretical framework | guide to organizing, what is a research methodology | steps & tips, how to write a research proposal | examples & templates, what is your plagiarism score.

Purdue Online Writing Lab Purdue OWL® College of Liberal Arts

Writing a Literature Review

Welcome to the Purdue OWL

This page is brought to you by the OWL at Purdue University. When printing this page, you must include the entire legal notice.

Copyright ©1995-2018 by The Writing Lab & The OWL at Purdue and Purdue University. All rights reserved. This material may not be published, reproduced, broadcast, rewritten, or redistributed without permission. Use of this site constitutes acceptance of our terms and conditions of fair use.

A literature review is a document or section of a document that collects key sources on a topic and discusses those sources in conversation with each other (also called synthesis ). The lit review is an important genre in many disciplines, not just literature (i.e., the study of works of literature such as novels and plays). When we say “literature review” or refer to “the literature,” we are talking about the research ( scholarship ) in a given field. You will often see the terms “the research,” “the scholarship,” and “the literature” used mostly interchangeably.

Where, when, and why would I write a lit review?

There are a number of different situations where you might write a literature review, each with slightly different expectations; different disciplines, too, have field-specific expectations for what a literature review is and does. For instance, in the humanities, authors might include more overt argumentation and interpretation of source material in their literature reviews, whereas in the sciences, authors are more likely to report study designs and results in their literature reviews; these differences reflect these disciplines’ purposes and conventions in scholarship. You should always look at examples from your own discipline and talk to professors or mentors in your field to be sure you understand your discipline’s conventions, for literature reviews as well as for any other genre.

A literature review can be a part of a research paper or scholarly article, usually falling after the introduction and before the research methods sections. In these cases, the lit review just needs to cover scholarship that is important to the issue you are writing about; sometimes it will also cover key sources that informed your research methodology.

Lit reviews can also be standalone pieces, either as assignments in a class or as publications. In a class, a lit review may be assigned to help students familiarize themselves with a topic and with scholarship in their field, get an idea of the other researchers working on the topic they’re interested in, find gaps in existing research in order to propose new projects, and/or develop a theoretical framework and methodology for later research. As a publication, a lit review usually is meant to help make other scholars’ lives easier by collecting and summarizing, synthesizing, and analyzing existing research on a topic. This can be especially helpful for students or scholars getting into a new research area, or for directing an entire community of scholars toward questions that have not yet been answered.

What are the parts of a lit review?

Most lit reviews use a basic introduction-body-conclusion structure; if your lit review is part of a larger paper, the introduction and conclusion pieces may be just a few sentences while you focus most of your attention on the body. If your lit review is a standalone piece, the introduction and conclusion take up more space and give you a place to discuss your goals, research methods, and conclusions separately from where you discuss the literature itself.

Introduction:

• An introductory paragraph that explains what your working topic and thesis is
• A forecast of key topics or texts that will appear in the review
• Potentially, a description of how you found sources and how you analyzed them for inclusion and discussion in the review (more often found in published, standalone literature reviews than in lit review sections in an article or research paper)
• Summarize and synthesize: Give an overview of the main points of each source and combine them into a coherent whole
• Analyze and interpret: Don’t just paraphrase other researchers – add your own interpretations where possible, discussing the significance of findings in relation to the literature as a whole
• Critically Evaluate: Mention the strengths and weaknesses of your sources
• Write in well-structured paragraphs: Use transition words and topic sentence to draw connections, comparisons, and contrasts.

Conclusion:

• Summarize the key findings you have taken from the literature and emphasize their significance
• Connect it back to your primary research question

How should I organize my lit review?

Lit reviews can take many different organizational patterns depending on what you are trying to accomplish with the review. Here are some examples:

• Chronological : The simplest approach is to trace the development of the topic over time, which helps familiarize the audience with the topic (for instance if you are introducing something that is not commonly known in your field). If you choose this strategy, be careful to avoid simply listing and summarizing sources in order. Try to analyze the patterns, turning points, and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred (as mentioned previously, this may not be appropriate in your discipline — check with a teacher or mentor if you’re unsure).
• Thematic : If you have found some recurring central themes that you will continue working with throughout your piece, you can organize your literature review into subsections that address different aspects of the topic. For example, if you are reviewing literature about women and religion, key themes can include the role of women in churches and the religious attitude towards women.
• Qualitative versus quantitative research
• Empirical versus theoretical scholarship
• Divide the research by sociological, historical, or cultural sources
• Theoretical : In many humanities articles, the literature review is the foundation for the theoretical framework. You can use it to discuss various theories, models, and definitions of key concepts. You can argue for the relevance of a specific theoretical approach or combine various theorical concepts to create a framework for your research.

What are some strategies or tips I can use while writing my lit review?

Any lit review is only as good as the research it discusses; make sure your sources are well-chosen and your research is thorough. Don’t be afraid to do more research if you discover a new thread as you’re writing. More info on the research process is available in our "Conducting Research" resources .

As you’re doing your research, create an annotated bibliography ( see our page on the this type of document ). Much of the information used in an annotated bibliography can be used also in a literature review, so you’ll be not only partially drafting your lit review as you research, but also developing your sense of the larger conversation going on among scholars, professionals, and any other stakeholders in your topic.

Usually you will need to synthesize research rather than just summarizing it. This means drawing connections between sources to create a picture of the scholarly conversation on a topic over time. Many student writers struggle to synthesize because they feel they don’t have anything to add to the scholars they are citing; here are some strategies to help you:

• It often helps to remember that the point of these kinds of syntheses is to show your readers how you understand your research, to help them read the rest of your paper.
• Writing teachers often say synthesis is like hosting a dinner party: imagine all your sources are together in a room, discussing your topic. What are they saying to each other?
• Look at the in-text citations in each paragraph. Are you citing just one source for each paragraph? This usually indicates summary only. When you have multiple sources cited in a paragraph, you are more likely to be synthesizing them (not always, but often
• Read more about synthesis here.

The most interesting literature reviews are often written as arguments (again, as mentioned at the beginning of the page, this is discipline-specific and doesn’t work for all situations). Often, the literature review is where you can establish your research as filling a particular gap or as relevant in a particular way. You have some chance to do this in your introduction in an article, but the literature review section gives a more extended opportunity to establish the conversation in the way you would like your readers to see it. You can choose the intellectual lineage you would like to be part of and whose definitions matter most to your thinking (mostly humanities-specific, but this goes for sciences as well). In addressing these points, you argue for your place in the conversation, which tends to make the lit review more compelling than a simple reporting of other sources.

Literature Review Research

Literature review, types of literature reviews.

• Finding information
• Additional Resources
• Explains the background of research on a topic
• Demonstrates why a topic is significant to a subject area
• Helps focus your own research questions or problems
• Discovers relationships between research studies/ideas
• Suggests unexplored ideas or populations
• Identifies major themes, concepts, and researchers on a topic
• Tests assumptions; may help counter preconceived ideas and remove unconscious bias.
• Identifies critical gaps, points of disagreement, or potentially flawed methodology or theoretical approaches

Argumentative Review This form examines literature selectively in order to support or refute an argument, deeply imbedded assumption, or philosophical problem already established in the literature. 

Integrative Review Considered a form of research that reviews, critiques, and synthesizes representative literature on a topic in an integrated way such that new frameworks and perspectives on the topic are generated. The body of literature includes all studies that address related or identical hypotheses. A well-done integrative review meets the same standards as primary research in regard to clarity, rigor, and replication.

Historical Review Historical reviews are focused on examining research throughout a period of time, often starting with the first time an issue, concept, theory, phenomena emerged in the literature, then tracing its evolution within the scholarship of a discipline. The purpose is to place research in a historical context to show familiarity with state-of-the-art developments and to identify the likely directions for future research.

Methodological Review This approach provides a framework of understanding at different levels (i.e. those of theory, substantive fields, research approaches and data collection and analysis techniques), enables researchers to draw on a wide variety of knowledge ranging from the conceptual level to practical documents for use in fieldwork.

Systematic Review Uses pre-specified and standardized methods to identify and critically appraise relevant research, and to collect, report, and analyze data from the studies that are included in the review. Typically it focuses on a very specific empirical question.

Theoretical Review

Examines the theory that has accumulated in regard to an issue, concept, theory, phenomena. Helps to establish what theories already exist, the relationships between them, to what degree the existing theories have been investigated, and to develop new hypotheses to be tested. Often this form is used to help establish a lack of appropriate theories or reveal that current theories are inadequate for explaining new or emerging research problems.

* Kennedy, Mary M. "Defining a Literature."  Educational Researcher  36 (April 2007): 139-147.

All content in this section is from The Literature Review created by Dr. Robert Larabee USC

• Next: Finding information >>
• Last Updated: Oct 26, 2023 8:34 PM
• URL: https://guides.lib.odu.edu/literaturereview

• UConn Library
• Literature Review: The What, Why and How-to Guide
• Introduction

Literature Review: The What, Why and How-to Guide — Introduction

• Getting Started
• How to Pick a Topic
• Strategies to Find Sources
• Evaluating Sources & Lit. Reviews
• Tips for Writing Literature Reviews
• Writing Literature Review: Useful Sites
• Citation Resources
• Other Academic Writings

What are Literature Reviews?

So, what is a literature review? "A literature review is an account of what has been published on a topic by accredited scholars and researchers. In writing the literature review, your purpose is to convey to your reader what knowledge and ideas have been established on a topic, and what their strengths and weaknesses are. As a piece of writing, the literature review must be defined by a guiding concept (e.g., your research objective, the problem or issue you are discussing, or your argumentative thesis). It is not just a descriptive list of the material available, or a set of summaries." Taylor, D.  The literature review: A few tips on conducting it . University of Toronto Health Sciences Writing Centre.

Goals of Literature Reviews

What are the goals of creating a Literature Review?  A literature could be written to accomplish different aims:

• To develop a theory or evaluate an existing theory
• To summarize the historical or existing state of a research topic
• Identify a problem in a field of research 

Baumeister, R. F., & Leary, M. R. (1997). Writing narrative literature reviews .  Review of General Psychology , 1 (3), 311-320.

What kinds of sources require a Literature Review?

• A research paper assigned in a course
• A thesis or dissertation
• A grant proposal
• An article intended for publication in a journal

All these instances require you to collect what has been written about your research topic so that you can demonstrate how your own research sheds new light on the topic.

Types of Literature Reviews

What kinds of literature reviews are written?

Narrative review: The purpose of this type of review is to describe the current state of the research on a specific topic/research and to offer a critical analysis of the literature reviewed. Studies are grouped by research/theoretical categories, and themes and trends, strengths and weakness, and gaps are identified. The review ends with a conclusion section which summarizes the findings regarding the state of the research of the specific study, the gaps identify and if applicable, explains how the author's research will address gaps identify in the review and expand the knowledge on the topic reviewed.

• Example : Predictors and Outcomes of U.S. Quality Maternity Leave: A Review and Conceptual Framework:  10.1177/08948453211037398  

Systematic review : "The authors of a systematic review use a specific procedure to search the research literature, select the studies to include in their review, and critically evaluate the studies they find." (p. 139). Nelson, L. K. (2013). Research in Communication Sciences and Disorders . Plural Publishing.

• Example : The effect of leave policies on increasing fertility: a systematic review:  10.1057/s41599-022-01270-w

Meta-analysis : "Meta-analysis is a method of reviewing research findings in a quantitative fashion by transforming the data from individual studies into what is called an effect size and then pooling and analyzing this information. The basic goal in meta-analysis is to explain why different outcomes have occurred in different studies." (p. 197). Roberts, M. C., & Ilardi, S. S. (2003). Handbook of Research Methods in Clinical Psychology . Blackwell Publishing.

• Example : Employment Instability and Fertility in Europe: A Meta-Analysis:  10.1215/00703370-9164737

Meta-synthesis : "Qualitative meta-synthesis is a type of qualitative study that uses as data the findings from other qualitative studies linked by the same or related topic." (p.312). Zimmer, L. (2006). Qualitative meta-synthesis: A question of dialoguing with texts .  Journal of Advanced Nursing , 53 (3), 311-318.

• Example : Women’s perspectives on career successes and barriers: A qualitative meta-synthesis:  10.1177/05390184221113735

Literature Reviews in the Health Sciences

• UConn Health subject guide on systematic reviews Explanation of the different review types used in health sciences literature as well as tools to help you find the right review type
• << Previous: Getting Started
• Next: How to Pick a Topic >>
• Last Updated: Sep 21, 2022 2:16 PM
• URL: https://guides.lib.uconn.edu/literaturereview

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, automatically generate references for free.

• Knowledge Base
• Dissertation
• What is a Literature Review? | Guide, Template, & Examples

What is a Literature Review? | Guide, Template, & Examples

Published on 22 February 2022 by Shona McCombes . Revised on 7 June 2022.

What is a literature review? A literature review is a survey of scholarly sources on a specific topic. It provides an overview of current knowledge, allowing you to identify relevant theories, methods, and gaps in the existing research.

There are five key steps to writing a literature review:

• Search for relevant literature
• Evaluate sources
• Identify themes, debates and gaps
• Outline the structure
• Write your literature review

A good literature review doesn’t just summarise sources – it analyses, synthesises, and critically evaluates to give a clear picture of the state of knowledge on the subject.

Table of contents

Why write a literature review, examples of literature reviews, step 1: search for relevant literature, step 2: evaluate and select sources, step 3: identify themes, debates and gaps, step 4: outline your literature review’s structure, step 5: write your literature review, frequently asked questions about literature reviews, introduction.

• Quick Run-through
• Step 1 & 2

When you write a dissertation or thesis, you will have to conduct a literature review to situate your research within existing knowledge. The literature review gives you a chance to:

• Demonstrate your familiarity with the topic and scholarly context
• Develop a theoretical framework and methodology for your research
• Position yourself in relation to other researchers and theorists
• Show how your dissertation addresses a gap or contributes to a debate

You might also have to write a literature review as a stand-alone assignment. In this case, the purpose is to evaluate the current state of research and demonstrate your knowledge of scholarly debates around a topic.

The content will look slightly different in each case, but the process of conducting a literature review follows the same steps. We’ve written a step-by-step guide that you can follow below.

Prevent plagiarism, run a free check.

Writing literature reviews can be quite challenging! A good starting point could be to look at some examples, depending on what kind of literature review you’d like to write.

• Example literature review #1: “Why Do People Migrate? A Review of the Theoretical Literature” ( Theoretical literature review about the development of economic migration theory from the 1950s to today.)
• Example literature review #2: “Literature review as a research methodology: An overview and guidelines” ( Methodological literature review about interdisciplinary knowledge acquisition and production.)
• Example literature review #3: “The Use of Technology in English Language Learning: A Literature Review” ( Thematic literature review about the effects of technology on language acquisition.)
• Example literature review #4: “Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review” ( Chronological literature review about how the concept of listening skills has changed over time.)

You can also check out our templates with literature review examples and sample outlines at the links below.

Download Word doc Download Google doc

Before you begin searching for literature, you need a clearly defined topic .

If you are writing the literature review section of a dissertation or research paper, you will search for literature related to your research objectives and questions .

If you are writing a literature review as a stand-alone assignment, you will have to choose a focus and develop a central question to direct your search. Unlike a dissertation research question, this question has to be answerable without collecting original data. You should be able to answer it based only on a review of existing publications.

Make a list of keywords

Start by creating a list of keywords related to your research topic. Include each of the key concepts or variables you’re interested in, and list any synonyms and related terms. You can add to this list if you discover new keywords in the process of your literature search.

• Social media, Facebook, Instagram, Twitter, Snapchat, TikTok
• Body image, self-perception, self-esteem, mental health
• Generation Z, teenagers, adolescents, youth

Search for relevant sources

Use your keywords to begin searching for sources. Some databases to search for journals and articles include:

• Your university’s library catalogue
• Google Scholar
• Project Muse (humanities and social sciences)
• Medline (life sciences and biomedicine)
• EconLit (economics)
• Inspec (physics, engineering and computer science)

You can use boolean operators to help narrow down your search:

Read the abstract to find out whether an article is relevant to your question. When you find a useful book or article, you can check the bibliography to find other relevant sources.

To identify the most important publications on your topic, take note of recurring citations. If the same authors, books or articles keep appearing in your reading, make sure to seek them out.

You probably won’t be able to read absolutely everything that has been written on the topic – you’ll have to evaluate which sources are most relevant to your questions.

For each publication, ask yourself:

• What question or problem is the author addressing?
• What are the key concepts and how are they defined?
• What are the key theories, models and methods? Does the research use established frameworks or take an innovative approach?
• What are the results and conclusions of the study?
• How does the publication relate to other literature in the field? Does it confirm, add to, or challenge established knowledge?
• How does the publication contribute to your understanding of the topic? What are its key insights and arguments?
• What are the strengths and weaknesses of the research?

Make sure the sources you use are credible, and make sure you read any landmark studies and major theories in your field of research.

You can find out how many times an article has been cited on Google Scholar – a high citation count means the article has been influential in the field, and should certainly be included in your literature review.

The scope of your review will depend on your topic and discipline: in the sciences you usually only review recent literature, but in the humanities you might take a long historical perspective (for example, to trace how a concept has changed in meaning over time).

Remember that you can use our template to summarise and evaluate sources you’re thinking about using!

Take notes and cite your sources

As you read, you should also begin the writing process. Take notes that you can later incorporate into the text of your literature review.

It’s important to keep track of your sources with references to avoid plagiarism . It can be helpful to make an annotated bibliography, where you compile full reference information and write a paragraph of summary and analysis for each source. This helps you remember what you read and saves time later in the process.

You can use our free APA Reference Generator for quick, correct, consistent citations.

To begin organising your literature review’s argument and structure, you need to understand the connections and relationships between the sources you’ve read. Based on your reading and notes, you can look for:

• Trends and patterns (in theory, method or results): do certain approaches become more or less popular over time?
• Themes: what questions or concepts recur across the literature?
• Debates, conflicts and contradictions: where do sources disagree?
• Pivotal publications: are there any influential theories or studies that changed the direction of the field?
• Gaps: what is missing from the literature? Are there weaknesses that need to be addressed?

This step will help you work out the structure of your literature review and (if applicable) show how your own research will contribute to existing knowledge.

• Most research has focused on young women.
• There is an increasing interest in the visual aspects of social media.
• But there is still a lack of robust research on highly-visual platforms like Instagram and Snapchat – this is a gap that you could address in your own research.

There are various approaches to organising the body of a literature review. You should have a rough idea of your strategy before you start writing.

Depending on the length of your literature review, you can combine several of these strategies (for example, your overall structure might be thematic, but each theme is discussed chronologically).

Chronological

The simplest approach is to trace the development of the topic over time. However, if you choose this strategy, be careful to avoid simply listing and summarising sources in order.

Try to analyse patterns, turning points and key debates that have shaped the direction of the field. Give your interpretation of how and why certain developments occurred.

If you have found some recurring central themes, you can organise your literature review into subsections that address different aspects of the topic.

For example, if you are reviewing literature about inequalities in migrant health outcomes, key themes might include healthcare policy, language barriers, cultural attitudes, legal status, and economic access.

Methodological

If you draw your sources from different disciplines or fields that use a variety of research methods , you might want to compare the results and conclusions that emerge from different approaches. For example:

• Look at what results have emerged in qualitative versus quantitative research
• Discuss how the topic has been approached by empirical versus theoretical scholarship
• Divide the literature into sociological, historical, and cultural sources

Theoretical

A literature review is often the foundation for a theoretical framework . You can use it to discuss various theories, models, and definitions of key concepts.

You might argue for the relevance of a specific theoretical approach, or combine various theoretical concepts to create a framework for your research.

Like any other academic text, your literature review should have an introduction , a main body, and a conclusion . What you include in each depends on the objective of your literature review.

The introduction should clearly establish the focus and purpose of the literature review.

If you are writing the literature review as part of your dissertation or thesis, reiterate your central problem or research question and give a brief summary of the scholarly context. You can emphasise the timeliness of the topic (“many recent studies have focused on the problem of x”) or highlight a gap in the literature (“while there has been much research on x, few researchers have taken y into consideration”).

Depending on the length of your literature review, you might want to divide the body into subsections. You can use a subheading for each theme, time period, or methodological approach.

As you write, make sure to follow these tips:

• Summarise and synthesise: give an overview of the main points of each source and combine them into a coherent whole.
• Analyse and interpret: don’t just paraphrase other researchers – add your own interpretations, discussing the significance of findings in relation to the literature as a whole.
• Critically evaluate: mention the strengths and weaknesses of your sources.
• Write in well-structured paragraphs: use transitions and topic sentences to draw connections, comparisons and contrasts.

In the conclusion, you should summarise the key findings you have taken from the literature and emphasise their significance.

If the literature review is part of your dissertation or thesis, reiterate how your research addresses gaps and contributes new knowledge, or discuss how you have drawn on existing theories and methods to build a framework for your research. This can lead directly into your methodology section.

A literature review is a survey of scholarly sources (such as books, journal articles, and theses) related to a specific topic or research question .

It is often written as part of a dissertation , thesis, research paper , or proposal .

There are several reasons to conduct a literature review at the beginning of a research project:

• To familiarise yourself with the current state of knowledge on your topic
• To ensure that you’re not just repeating what others have already done
• To identify gaps in knowledge and unresolved problems that your research can address
• To develop your theoretical framework and methodology
• To provide an overview of the key findings and debates on the topic

Writing the literature review shows your reader how your work relates to existing research and what new insights it will contribute.

The literature review usually comes near the beginning of your  dissertation . After the introduction , it grounds your research in a scholarly field and leads directly to your theoretical framework or methodology .

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

McCombes, S. (2022, June 07). What is a Literature Review? | Guide, Template, & Examples. Scribbr. Retrieved 14 November 2023, from https://www.scribbr.co.uk/thesis-dissertation/literature-review/

Is this article helpful?

Shona McCombes

Other students also liked, how to write a dissertation proposal | a step-by-step guide, what is a theoretical framework | a step-by-step guide, what is a research methodology | steps & tips.

Harvey Cushing/John Hay Whitney Medical Library

• Collections
• Research Help

YSN Doctoral Programs: Steps in Conducting a Literature Review

• Biomedical Databases
• Global (Public Health) Databases
• Soc. Sci., History, and Law Databases
• Grey Literature
• Trials Registers
• Data and Statistics
• Public Policy
• Google Tips
• Recommended Books
• Steps in Conducting a Literature Review

What is a literature review?

A literature review is an integrated analysis -- not just a summary-- of scholarly writings and other relevant evidence related directly to your research question.  That is, it represents a synthesis of the evidence that provides background information on your topic and shows a association between the evidence and your research question.

A literature review may be a stand alone work or the introduction to a larger research paper, depending on the assignment.  Rely heavily on the guidelines your instructor has given you.

Why is it important?

A literature review is important because it:

• Explains the background of research on a topic.
• Demonstrates why a topic is significant to a subject area.
• Discovers relationships between research studies/ideas.
• Identifies major themes, concepts, and researchers on a topic.
• Identifies critical gaps and points of disagreement.
• Discusses further research questions that logically come out of the previous studies.

APA7 Style resources

APA Style Blog - for those harder to find answers

1. Choose a topic. Define your research question.

Your literature review should be guided by your central research question.  The literature represents background and research developments related to a specific research question, interpreted and analyzed by you in a synthesized way.

• Make sure your research question is not too broad or too narrow.  Is it manageable?
• Begin writing down terms that are related to your question. These will be useful for searches later.
• If you have the opportunity, discuss your topic with your professor and your class mates.

2. Decide on the scope of your review

How many studies do you need to look at? How comprehensive should it be? How many years should it cover? 

• This may depend on your assignment.  How many sources does the assignment require?

3. Select the databases you will use to conduct your searches.

Make a list of the databases you will search. 

Where to find databases:

• use the tabs on this guide
• Find other databases in the Nursing Information Resources web page
• More on the Medical Library web page
• ... and more on the Yale University Library web page

4. Conduct your searches to find the evidence. Keep track of your searches.

• Use the key words in your question, as well as synonyms for those words, as terms in your search. Use the database tutorials for help.
• Save the searches in the databases. This saves time when you want to redo, or modify, the searches. It is also helpful to use as a guide is the searches are not finding any useful results.
• Review the abstracts of research studies carefully. This will save you time.
• Use the bibliographies and references of research studies you find to locate others.
• Check with your professor, or a subject expert in the field, if you are missing any key works in the field.
• Ask your librarian for help at any time.
• Use a citation manager, such as EndNote as the repository for your citations. See the EndNote tutorials for help.

Review the literature

Some questions to help you analyze the research:

• What was the research question of the study you are reviewing? What were the authors trying to discover?
• Was the research funded by a source that could influence the findings?
• What were the research methodologies? Analyze its literature review, the samples and variables used, the results, and the conclusions.
• Does the research seem to be complete? Could it have been conducted more soundly? What further questions does it raise?
• If there are conflicting studies, why do you think that is?
• How are the authors viewed in the field? Has this study been cited? If so, how has it been analyzed?

Tips: 

• Review the abstracts carefully.  
• Keep careful notes so that you may track your thought processes during the research process.
• Create a matrix of the studies for easy analysis, and synthesis, across all of the studies.
• << Previous: Recommended Books
• Last Updated: Oct 31, 2023 3:00 PM
• URL: https://guides.library.yale.edu/YSNDoctoral

• USC Libraries
• Research Guides

Organizing Your Social Sciences Research Paper

• 5. The Literature Review
• Purpose of Guide
• Design Flaws to Avoid
• Independent and Dependent Variables
• Glossary of Research Terms
• Reading Research Effectively
• Narrowing a Topic Idea
• Broadening a Topic Idea
• Extending the Timeliness of a Topic Idea
• Academic Writing Style
• Choosing a Title
• Making an Outline
• Paragraph Development
• Research Process Video Series
• Executive Summary
• The C.A.R.S. Model
• Background Information
• The Research Problem/Question
• Theoretical Framework
• Citation Tracking
• Content Alert Services
• Evaluating Sources
• Primary Sources
• Secondary Sources
• Tiertiary Sources
• Scholarly vs. Popular Publications
• Qualitative Methods
• Quantitative Methods
• Insiderness
• Using Non-Textual Elements
• Limitations of the Study
• Common Grammar Mistakes
• Writing Concisely
• Avoiding Plagiarism
• Footnotes or Endnotes?
• Further Readings
• Generative AI and Writing
• USC Libraries Tutorials and Other Guides
• Bibliography

A literature review surveys prior research published in books, scholarly articles, and any other sources relevant to a particular issue, area of research, or theory, and by so doing, provides a description, summary, and critical evaluation of these works in relation to the research problem being investigated. Literature reviews are designed to provide an overview of sources you have used in researching a particular topic and to demonstrate to your readers how your research fits within existing scholarship about the topic.

Fink, Arlene. Conducting Research Literature Reviews: From the Internet to Paper . Fourth edition. Thousand Oaks, CA: SAGE, 2014.

Importance of a Good Literature Review

A literature review may consist of simply a summary of key sources, but in the social sciences, a literature review usually has an organizational pattern and combines both summary and synthesis, often within specific conceptual categories . A summary is a recap of the important information of the source, but a synthesis is a re-organization, or a reshuffling, of that information in a way that informs how you are planning to investigate a research problem. The analytical features of a literature review might:

• Give a new interpretation of old material or combine new with old interpretations,
• Trace the intellectual progression of the field, including major debates,
• Depending on the situation, evaluate the sources and advise the reader on the most pertinent or relevant research, or
• Usually in the conclusion of a literature review, identify where gaps exist in how a problem has been researched to date.

Given this, the purpose of a literature review is to:

• Place each work in the context of its contribution to understanding the research problem being studied.
• Describe the relationship of each work to the others under consideration.
• Identify new ways to interpret prior research.
• Reveal any gaps that exist in the literature.
• Resolve conflicts amongst seemingly contradictory previous studies.
• Identify areas of prior scholarship to prevent duplication of effort.
• Point the way in fulfilling a need for additional research.
• Locate your own research within the context of existing literature [very important].

Fink, Arlene. Conducting Research Literature Reviews: From the Internet to Paper. 2nd ed. Thousand Oaks, CA: Sage, 2005; Hart, Chris. Doing a Literature Review: Releasing the Social Science Research Imagination . Thousand Oaks, CA: Sage Publications, 1998; Jesson, Jill. Doing Your Literature Review: Traditional and Systematic Techniques . Los Angeles, CA: SAGE, 2011; Knopf, Jeffrey W. "Doing a Literature Review." PS: Political Science and Politics 39 (January 2006): 127-132; Ridley, Diana. The Literature Review: A Step-by-Step Guide for Students . 2nd ed. Los Angeles, CA: SAGE, 2012.

Types of Literature Reviews

It is important to think of knowledge in a given field as consisting of three layers. First, there are the primary studies that researchers conduct and publish. Second are the reviews of those studies that summarize and offer new interpretations built from and often extending beyond the primary studies. Third, there are the perceptions, conclusions, opinion, and interpretations that are shared informally among scholars that become part of the body of epistemological traditions within the field.

In composing a literature review, it is important to note that it is often this third layer of knowledge that is cited as "true" even though it often has only a loose relationship to the primary studies and secondary literature reviews. Given this, while literature reviews are designed to provide an overview and synthesis of pertinent sources you have explored, there are a number of approaches you could adopt depending upon the type of analysis underpinning your study.

Argumentative Review This form examines literature selectively in order to support or refute an argument, deeply embedded assumption, or philosophical problem already established in the literature. The purpose is to develop a body of literature that establishes a contrarian viewpoint. Given the value-laden nature of some social science research [e.g., educational reform; immigration control], argumentative approaches to analyzing the literature can be a legitimate and important form of discourse. However, note that they can also introduce problems of bias when they are used to make summary claims of the sort found in systematic reviews [see below].

Integrative Review Considered a form of research that reviews, critiques, and synthesizes representative literature on a topic in an integrated way such that new frameworks and perspectives on the topic are generated. The body of literature includes all studies that address related or identical hypotheses or research problems. A well-done integrative review meets the same standards as primary research in regard to clarity, rigor, and replication. This is the most common form of review in the social sciences.

Historical Review Few things rest in isolation from historical precedent. Historical literature reviews focus on examining research throughout a period of time, often starting with the first time an issue, concept, theory, phenomena emerged in the literature, then tracing its evolution within the scholarship of a discipline. The purpose is to place research in a historical context to show familiarity with state-of-the-art developments and to identify the likely directions for future research.

Methodological Review A review does not always focus on what someone said [findings], but how they came about saying what they say [method of analysis]. Reviewing methods of analysis provides a framework of understanding at different levels [i.e. those of theory, substantive fields, research approaches, and data collection and analysis techniques], how researchers draw upon a wide variety of knowledge ranging from the conceptual level to practical documents for use in fieldwork in the areas of ontological and epistemological consideration, quantitative and qualitative integration, sampling, interviewing, data collection, and data analysis. This approach helps highlight ethical issues which you should be aware of and consider as you go through your own study.

Systematic Review This form consists of an overview of existing evidence pertinent to a clearly formulated research question, which uses pre-specified and standardized methods to identify and critically appraise relevant research, and to collect, report, and analyze data from the studies that are included in the review. The goal is to deliberately document, critically evaluate, and summarize scientifically all of the research about a clearly defined research problem . Typically it focuses on a very specific empirical question, often posed in a cause-and-effect form, such as "To what extent does A contribute to B?" This type of literature review is primarily applied to examining prior research studies in clinical medicine and allied health fields, but it is increasingly being used in the social sciences.

Theoretical Review The purpose of this form is to examine the corpus of theory that has accumulated in regard to an issue, concept, theory, phenomena. The theoretical literature review helps to establish what theories already exist, the relationships between them, to what degree the existing theories have been investigated, and to develop new hypotheses to be tested. Often this form is used to help establish a lack of appropriate theories or reveal that current theories are inadequate for explaining new or emerging research problems. The unit of analysis can focus on a theoretical concept or a whole theory or framework.

NOTE : Most often the literature review will incorporate some combination of types. For example, a review that examines literature supporting or refuting an argument, assumption, or philosophical problem related to the research problem will also need to include writing supported by sources that establish the history of these arguments in the literature.

Baumeister, Roy F. and Mark R. Leary. "Writing Narrative Literature Reviews."  Review of General Psychology 1 (September 1997): 311-320; Mark R. Fink, Arlene. Conducting Research Literature Reviews: From the Internet to Paper . 2nd ed. Thousand Oaks, CA: Sage, 2005; Hart, Chris. Doing a Literature Review: Releasing the Social Science Research Imagination . Thousand Oaks, CA: Sage Publications, 1998; Kennedy, Mary M. "Defining a Literature." Educational Researcher 36 (April 2007): 139-147; Petticrew, Mark and Helen Roberts. Systematic Reviews in the Social Sciences: A Practical Guide . Malden, MA: Blackwell Publishers, 2006; Torracro, Richard. "Writing Integrative Literature Reviews: Guidelines and Examples." Human Resource Development Review 4 (September 2005): 356-367; Rocco, Tonette S. and Maria S. Plakhotnik. "Literature Reviews, Conceptual Frameworks, and Theoretical Frameworks: Terms, Functions, and Distinctions." Human Ressource Development Review 8 (March 2008): 120-130; Sutton, Anthea. Systematic Approaches to a Successful Literature Review . Los Angeles, CA: Sage Publications, 2016.

Structure and Writing Style

I.  Thinking About Your Literature Review

The structure of a literature review should include the following in support of understanding the research problem :

• An overview of the subject, issue, or theory under consideration, along with the objectives of the literature review,
• Division of works under review into themes or categories [e.g. works that support a particular position, those against, and those offering alternative approaches entirely],
• An explanation of how each work is similar to and how it varies from the others,
• Conclusions as to which pieces are best considered in their argument, are most convincing of their opinions, and make the greatest contribution to the understanding and development of their area of research.

The critical evaluation of each work should consider :

• Provenance -- what are the author's credentials? Are the author's arguments supported by evidence [e.g. primary historical material, case studies, narratives, statistics, recent scientific findings]?
• Methodology -- were the techniques used to identify, gather, and analyze the data appropriate to addressing the research problem? Was the sample size appropriate? Were the results effectively interpreted and reported?
• Objectivity -- is the author's perspective even-handed or prejudicial? Is contrary data considered or is certain pertinent information ignored to prove the author's point?
• Persuasiveness -- which of the author's theses are most convincing or least convincing?
• Validity -- are the author's arguments and conclusions convincing? Does the work ultimately contribute in any significant way to an understanding of the subject?

II.  Development of the Literature Review

Four Basic Stages of Writing 1.  Problem formulation -- which topic or field is being examined and what are its component issues? 2.  Literature search -- finding materials relevant to the subject being explored. 3.  Data evaluation -- determining which literature makes a significant contribution to the understanding of the topic. 4.  Analysis and interpretation -- discussing the findings and conclusions of pertinent literature.

Consider the following issues before writing the literature review: Clarify If your assignment is not specific about what form your literature review should take, seek clarification from your professor by asking these questions: 1.  Roughly how many sources would be appropriate to include? 2.  What types of sources should I review (books, journal articles, websites; scholarly versus popular sources)? 3.  Should I summarize, synthesize, or critique sources by discussing a common theme or issue? 4.  Should I evaluate the sources in any way beyond evaluating how they relate to understanding the research problem? 5.  Should I provide subheadings and other background information, such as definitions and/or a history? Find Models Use the exercise of reviewing the literature to examine how authors in your discipline or area of interest have composed their literature review sections. Read them to get a sense of the types of themes you might want to look for in your own research or to identify ways to organize your final review. The bibliography or reference section of sources you've already read, such as required readings in the course syllabus, are also excellent entry points into your own research. Narrow the Topic The narrower your topic, the easier it will be to limit the number of sources you need to read in order to obtain a good survey of relevant resources. Your professor will probably not expect you to read everything that's available about the topic, but you'll make the act of reviewing easier if you first limit scope of the research problem. A good strategy is to begin by searching the USC Libraries Catalog for recent books about the topic and review the table of contents for chapters that focuses on specific issues. You can also review the indexes of books to find references to specific issues that can serve as the focus of your research. For example, a book surveying the history of the Israeli-Palestinian conflict may include a chapter on the role Egypt has played in mediating the conflict, or look in the index for the pages where Egypt is mentioned in the text. Consider Whether Your Sources are Current Some disciplines require that you use information that is as current as possible. This is particularly true in disciplines in medicine and the sciences where research conducted becomes obsolete very quickly as new discoveries are made. However, when writing a review in the social sciences, a survey of the history of the literature may be required. In other words, a complete understanding the research problem requires you to deliberately examine how knowledge and perspectives have changed over time. Sort through other current bibliographies or literature reviews in the field to get a sense of what your discipline expects. You can also use this method to explore what is considered by scholars to be a "hot topic" and what is not.

III.  Ways to Organize Your Literature Review

Chronology of Events If your review follows the chronological method, you could write about the materials according to when they were published. This approach should only be followed if a clear path of research building on previous research can be identified and that these trends follow a clear chronological order of development. For example, a literature review that focuses on continuing research about the emergence of German economic power after the fall of the Soviet Union. By Publication Order your sources by publication chronology, then, only if the order demonstrates a more important trend. For instance, you could order a review of literature on environmental studies of brown fields if the progression revealed, for example, a change in the soil collection practices of the researchers who wrote and/or conducted the studies. Thematic [“conceptual categories”] A thematic literature review is the most common approach to summarizing prior research in the social and behavioral sciences. Thematic reviews are organized around a topic or issue, rather than the progression of time, although the progression of time may still be incorporated into a thematic review. For example, a review of the Internet’s impact on American presidential politics could focus on the development of online political satire. While the study focuses on one topic, the Internet’s impact on American presidential politics, it would still be organized chronologically reflecting technological developments in media. The difference in this example between a "chronological" and a "thematic" approach is what is emphasized the most: themes related to the role of the Internet in presidential politics. Note that more authentic thematic reviews tend to break away from chronological order. A review organized in this manner would shift between time periods within each section according to the point being made. Methodological A methodological approach focuses on the methods utilized by the researcher. For the Internet in American presidential politics project, one methodological approach would be to look at cultural differences between the portrayal of American presidents on American, British, and French websites. Or the review might focus on the fundraising impact of the Internet on a particular political party. A methodological scope will influence either the types of documents in the review or the way in which these documents are discussed.

Other Sections of Your Literature Review Once you've decided on the organizational method for your literature review, the sections you need to include in the paper should be easy to figure out because they arise from your organizational strategy. In other words, a chronological review would have subsections for each vital time period; a thematic review would have subtopics based upon factors that relate to the theme or issue. However, sometimes you may need to add additional sections that are necessary for your study, but do not fit in the organizational strategy of the body. What other sections you include in the body is up to you. However, only include what is necessary for the reader to locate your study within the larger scholarship about the research problem.

Here are examples of other sections, usually in the form of a single paragraph, you may need to include depending on the type of review you write:

• Current Situation : Information necessary to understand the current topic or focus of the literature review.
• Sources Used : Describes the methods and resources [e.g., databases] you used to identify the literature you reviewed.
• History : The chronological progression of the field, the research literature, or an idea that is necessary to understand the literature review, if the body of the literature review is not already a chronology.
• Selection Methods : Criteria you used to select (and perhaps exclude) sources in your literature review. For instance, you might explain that your review includes only peer-reviewed [i.e., scholarly] sources.
• Standards : Description of the way in which you present your information.
• Questions for Further Research : What questions about the field has the review sparked? How will you further your research as a result of the review?

IV.  Writing Your Literature Review

Once you've settled on how to organize your literature review, you're ready to write each section. When writing your review, keep in mind these issues.

Use Evidence A literature review section is, in this sense, just like any other academic research paper. Your interpretation of the available sources must be backed up with evidence [citations] that demonstrates that what you are saying is valid. Be Selective Select only the most important points in each source to highlight in the review. The type of information you choose to mention should relate directly to the research problem, whether it is thematic, methodological, or chronological. Related items that provide additional information, but that are not key to understanding the research problem, can be included in a list of further readings . Use Quotes Sparingly Some short quotes are appropriate if you want to emphasize a point, or if what an author stated cannot be easily paraphrased. Sometimes you may need to quote certain terminology that was coined by the author, is not common knowledge, or taken directly from the study. Do not use extensive quotes as a substitute for using your own words in reviewing the literature. Summarize and Synthesize Remember to summarize and synthesize your sources within each thematic paragraph as well as throughout the review. Recapitulate important features of a research study, but then synthesize it by rephrasing the study's significance and relating it to your own work and the work of others. Keep Your Own Voice While the literature review presents others' ideas, your voice [the writer's] should remain front and center. For example, weave references to other sources into what you are writing but maintain your own voice by starting and ending the paragraph with your own ideas and wording. Use Caution When Paraphrasing When paraphrasing a source that is not your own, be sure to represent the author's information or opinions accurately and in your own words. Even when paraphrasing an author’s work, you still must provide a citation to that work.

V.  Common Mistakes to Avoid

These are the most common mistakes made in reviewing social science research literature.

• Sources in your literature review do not clearly relate to the research problem;
• You do not take sufficient time to define and identify the most relevant sources to use in the literature review related to the research problem;
• Relies exclusively on secondary analytical sources rather than including relevant primary research studies or data;
• Uncritically accepts another researcher's findings and interpretations as valid, rather than examining critically all aspects of the research design and analysis;
• Does not describe the search procedures that were used in identifying the literature to review;
• Reports isolated statistical results rather than synthesizing them in chi-squared or meta-analytic methods; and,
• Only includes research that validates assumptions and does not consider contrary findings and alternative interpretations found in the literature.

Cook, Kathleen E. and Elise Murowchick. “Do Literature Review Skills Transfer from One Course to Another?” Psychology Learning and Teaching 13 (March 2014): 3-11; Fink, Arlene. Conducting Research Literature Reviews: From the Internet to Paper . 2nd ed. Thousand Oaks, CA: Sage, 2005; Hart, Chris. Doing a Literature Review: Releasing the Social Science Research Imagination . Thousand Oaks, CA: Sage Publications, 1998; Jesson, Jill. Doing Your Literature Review: Traditional and Systematic Techniques . London: SAGE, 2011; Literature Review Handout. Online Writing Center. Liberty University; Literature Reviews. The Writing Center. University of North Carolina; Onwuegbuzie, Anthony J. and Rebecca Frels. Seven Steps to a Comprehensive Literature Review: A Multimodal and Cultural Approach . Los Angeles, CA: SAGE, 2016; Ridley, Diana. The Literature Review: A Step-by-Step Guide for Students . 2nd ed. Los Angeles, CA: SAGE, 2012; Randolph, Justus J. “A Guide to Writing the Dissertation Literature Review." Practical Assessment, Research, and Evaluation. vol. 14, June 2009; Sutton, Anthea. Systematic Approaches to a Successful Literature Review . Los Angeles, CA: Sage Publications, 2016; Taylor, Dena. The Literature Review: A Few Tips On Conducting It. University College Writing Centre. University of Toronto; Writing a Literature Review. Academic Skills Centre. University of Canberra.

Writing Tip

Break Out of Your Disciplinary Box!

Thinking interdisciplinarily about a research problem can be a rewarding exercise in applying new ideas, theories, or concepts to an old problem. For example, what might cultural anthropologists say about the continuing conflict in the Middle East? In what ways might geographers view the need for better distribution of social service agencies in large cities than how social workers might study the issue? You don’t want to substitute a thorough review of core research literature in your discipline for studies conducted in other fields of study. However, particularly in the social sciences, thinking about research problems from multiple vectors is a key strategy for finding new solutions to a problem or gaining a new perspective. Consult with a librarian about identifying research databases in other disciplines; almost every field of study has at least one comprehensive database devoted to indexing its research literature.

Frodeman, Robert. The Oxford Handbook of Interdisciplinarity . New York: Oxford University Press, 2010.

Another Writing Tip

Don't Just Review for Content!

While conducting a review of the literature, maximize the time you devote to writing this part of your paper by thinking broadly about what you should be looking for and evaluating. Review not just what scholars are saying, but how are they saying it. Some questions to ask:

• How are they organizing their ideas?
• What methods have they used to study the problem?
• What theories have been used to explain, predict, or understand their research problem?
• What sources have they cited to support their conclusions?
• How have they used non-textual elements [e.g., charts, graphs, figures, etc.] to illustrate key points?

When you begin to write your literature review section, you'll be glad you dug deeper into how the research was designed and constructed because it establishes a means for developing more substantial analysis and interpretation of the research problem.

Hart, Chris. Doing a Literature Review: Releasing the Social Science Research Imagination . Thousand Oaks, CA: Sage Publications, 1 998.

Yet Another Writing Tip

When Do I Know I Can Stop Looking and Move On?

Here are several strategies you can utilize to assess whether you've thoroughly reviewed the literature:

• Look for repeating patterns in the research findings . If the same thing is being said, just by different people, then this likely demonstrates that the research problem has hit a conceptual dead end. At this point consider: Does your study extend current research?  Does it forge a new path? Or, does is merely add more of the same thing being said?
• Look at sources the authors cite to in their work . If you begin to see the same researchers cited again and again, then this is often an indication that no new ideas have been generated to address the research problem.
• Search Google Scholar to identify who has subsequently cited leading scholars already identified in your literature review [see next sub-tab]. This is called citation tracking and there are a number of sources that can help you identify who has cited whom, particularly scholars from outside of your discipline. Here again, if the same authors are being cited again and again, this may indicate no new literature has been written on the topic.

Onwuegbuzie, Anthony J. and Rebecca Frels. Seven Steps to a Comprehensive Literature Review: A Multimodal and Cultural Approach . Los Angeles, CA: Sage, 2016; Sutton, Anthea. Systematic Approaches to a Successful Literature Review . Los Angeles, CA: Sage Publications, 2016.

• << Previous: Theoretical Framework
• Next: Citation Tracking >>
• Last Updated: Oct 10, 2023 1:30 PM
• URL: https://libguides.usc.edu/writingguide

• Maps & Floorplans
• Libraries A-Z

• Ellis Library (main)
• Engineering Library
• Geological Sciences
• Journalism Library
• Law Library
• Mathematical Sciences
• MU Digital Collections
• Veterinary Medical
• More Libraries...
• Instructional Services
• Course Reserves
• Course Guides
• Schedule a Library Class
• Class Assessment Forms
• Recordings & Tutorials
• Research & Writing Help
• More class resources
• Places to Study
• Borrow, Request & Renew
• Call Numbers
• Computers, Printers, Scanners & Software
• Digital Media Lab
• Equipment Lending: Laptops, cameras, etc.
• Subject Librarians
• Writing Tutors
• More In the Library...
• Undergraduate Students
• Graduate Students
• Faculty & Staff
• Researcher Support
• Distance Learners
• International Students
• More Services for...
• View my MU Libraries Account (login & click on My Library Account)
• View my MOBIUS Checkouts
• Renew my Books (login & click on My Loans)
• Place a Hold on a Book
• Request Books from Depository
• View my ILL@MU Account
• Set Up Alerts in Databases
• More Account Information...

Introduction to Literature Reviews

Introduction.

• Step One: Define
• Step Two: Research
• Step Three: Write
• Suggested Readings

A literature review is a written work that :

• Compiles significant research published on a topic by accredited scholars and researchers;
• —Surveys scholarly articles, books, dissertations, conference proceedings, and other sources;
• —Examines contrasting perspectives, theoretical approaches, methodologies, findings, results, conclusions.
• —Reviews critically, analyzes, and synthesizes existing research on a topic; and,
• Performs a thorough “re” view, “overview”, or “look again” of past and current works on a subject, issue, or theory.

From these analyses, the writer then offers an overview of the current status of a particular area of knowledge from both a practical and theoretical perspective.

Literature reviews are important because they are usually a  required  step in a thesis proposal (Master's or PhD). The proposal will not be well-supported without a literature review. Also, literature reviews are important because they help you learn important authors and ideas in your field. This is useful for your coursework and your writing. Knowing key authors also helps you become acquainted with other researchers in your field.

Look at this diagram and imagine that your research is the "something new." This shows how your research should relate to major works and other sources.

Olivia Whitfield | Graduate Reference Assistant | 2012-2015

• Next: Step One: Define >>
• Last Updated: Jun 28, 2023 5:49 PM
• URL: https://libraryguides.missouri.edu/literaturereview

WashU Libraries

Library services for undergraduate research.

• Creating an Abstract
• What is a Literature Review?
• Creating a Poster
• Presenting Your Research
• Share Your Undergraduate Research
• Contact a Subject Librarian This link opens in a new window
• Conducting Research
• College Writing: Citizen Scientist

Literature Review: A Definition

What is a literature review, then.

A literature review discusses and analyses published information in a particular subject area.   Sometimes the information covers a certain time period.

A literature review is more than a summary of the sources, it has an organizational pattern that combines both summary and synthesis. A summary is a recap of the important information of the source, but a synthesis is a re-organization, or a reshuffling, of that information. It might give a new interpretation of old material or combine new with old interpretations. Or it might trace the intellectual progression of the field, including major debates. And depending on the situation, the literature review may evaluate the sources and advise the reader on the most pertinent or relevant.

But how is a literature review different from an academic research paper?

While the main focus of an academic research paper is to support your own argument, the focus of a literature review is to summarize and synthesize the arguments and ideas of others. The academic research paper also covers a range of sources, but it is usually a select number of sources, because the emphasis is on the argument. Likewise, a literature review can also have an "argument," but it is not as important as covering a number of sources. In short, an academic research paper and a literature review contain some of the same elements. In fact, many academic research papers will contain a literature review section. What aspect of the study (either the argument or the sources) that is emphasized determines what type of document it is.

( "Literature Reviews" from The Writing Center, University of North Carolina at Chapel Hill )

Why do we write literature reviews?

Literature reviews provide you with a handy guide to a particular topic. If you have limited time to conduct research, literature reviews can give you an overview or act as a stepping stone.

For professionals, they are useful reports that keep them up to date with what is current in the field.

For scholars, the depth and breadth of the literature review emphasizes the credibility of the writer in his or her field. Literature reviews also provide a solid background for a research paper's investigation.

Comprehensive knowledge of the literature of the field is essential to most research papers.

Journal Articles on Writing Literature Reviews

• Research Methods for Comprehensive Science Literature Reviews Author: Brown,Barry N. Journal: Issues in Science & Technology Librarianship Date: Spring2009 Issue: 57 Page: 1 more... less... Finding some information on most topics is easy. There are abundant sources of information readily available. However, completing a comprehensive literature review on a particular topic is often difficult, laborious, and time intensive; the project requires organization, persistence, and an understanding of the scholarly communication and publishing process. This paper briefly outlines methods of conducting a comprehensive literature review for science topics. [ABSTRACT FROM AUTHOR];
• Research: Considerations in Writing a Literature Review Authors: Black,K. Journal: The New Social Worker Date: 01/01; 2007 Volume: 14 Issue: 2 Page: 12 more... less... Literature reviews are ubiquitous in academic journals, scholarly reports, and social work education. Conducting and writing a good literature review is both personally and professionally satisfying. (Journal abstract).
• How to do (or not to do) A Critical Literature Review Authors: Jesson,Jill; Lacey,Fiona Journal: Pharmacy Education Pub Date: 2006 Volume: 6 Issue: 2 Pages:139 - 148 more... less... More and more students are required to perform a critical literature review as part of their undergraduate or postgraduate studies. Whilst most of the latest research methods textbooks advise how to do a literature search, very few cover the literature review. This paper covers two types of review: a critical literature review and a systematic review. [ABSTRACT FROM AUTHOR]
• Conducting a Literature Review Authors: Rowley,Jennifer; Slack,Frances Journal: Management Research News Pub Date: 2004 Volume: 27 Issue: 6 Pages:31-39 more... less... Abstract: This article offers support and guidance for students undertaking a literature review as part of their dissertation during an undergraduate or Masters course. A literature review is a summary of a subject field that supports the identification of specific research questions. A literature review needs to draw on and evaluate a range of different types of sources including academic and professional journal articles, books, and web-based resources. The literature search helps in the identification and location of relevant documents and other sources. Search engines can be used to search web resources and bibliographic databases. Conceptual frameworks can be a useful tool in developing an understanding of a subject area. Creating the literature review involves the stages of: scanning, making notes, structuring the literature review, writing the literature review, and building a bibliography.

Some Books from the WU Catalog

• The SAGE handbook of visual research methods [electronic resource] by Edited by Luc Pauwels and Dawn Mannay. ISBN: 9781526417015 Publication Date: SAGE Publications, Inc., 2020.

Helpful Websites

• "How to do a Literature Review" from Ferdinand D. Bluford Library
• "The Literature Review: A Few Tips on Conducting It." from the University of Toronto
• << Previous: Creating an Abstract
• Next: Creating a Poster >>
• Last Updated: Mar 7, 2023 9:14 PM
• URL: https://libguides.wustl.edu/our

Literature Reviews

What this handout is about.

This handout will explain what literature reviews are and offer insights into the form and construction of literature reviews in the humanities, social sciences, and sciences.

Introduction

OK. You’ve got to write a literature review. You dust off a novel and a book of poetry, settle down in your chair, and get ready to issue a “thumbs up” or “thumbs down” as you leaf through the pages. “Literature review” done. Right?

Wrong! The “literature” of a literature review refers to any collection of materials on a topic, not necessarily the great literary texts of the world. “Literature” could be anything from a set of government pamphlets on British colonial methods in Africa to scholarly articles on the treatment of a torn ACL. And a review does not necessarily mean that your reader wants you to give your personal opinion on whether or not you liked these sources.

What is a literature review, then?

A literature review discusses published information in a particular subject area, and sometimes information in a particular subject area within a certain time period.

A literature review can be just a simple summary of the sources, but it usually has an organizational pattern and combines both summary and synthesis. A summary is a recap of the important information of the source, but a synthesis is a re-organization, or a reshuffling, of that information. It might give a new interpretation of old material or combine new with old interpretations. Or it might trace the intellectual progression of the field, including major debates. And depending on the situation, the literature review may evaluate the sources and advise the reader on the most pertinent or relevant.

But how is a literature review different from an academic research paper?

The main focus of an academic research paper is to develop a new argument, and a research paper is likely to contain a literature review as one of its parts. In a research paper, you use the literature as a foundation and as support for a new insight that you contribute. The focus of a literature review, however, is to summarize and synthesize the arguments and ideas of others without adding new contributions.

Why do we write literature reviews?

Literature reviews provide you with a handy guide to a particular topic. If you have limited time to conduct research, literature reviews can give you an overview or act as a stepping stone. For professionals, they are useful reports that keep them up to date with what is current in the field. For scholars, the depth and breadth of the literature review emphasizes the credibility of the writer in his or her field. Literature reviews also provide a solid background for a research paper’s investigation. Comprehensive knowledge of the literature of the field is essential to most research papers.

Who writes these things, anyway?

Literature reviews are written occasionally in the humanities, but mostly in the sciences and social sciences; in experiment and lab reports, they constitute a section of the paper. Sometimes a literature review is written as a paper in itself.

Let’s get to it! What should I do before writing the literature review?

If your assignment is not very specific, seek clarification from your instructor:

• Roughly how many sources should you include?
• What types of sources (books, journal articles, websites)?
• Should you summarize, synthesize, or critique your sources by discussing a common theme or issue?
• Should you evaluate your sources?
• Should you provide subheadings and other background information, such as definitions and/or a history?

Find models

Look for other literature reviews in your area of interest or in the discipline and read them to get a sense of the types of themes you might want to look for in your own research or ways to organize your final review. You can simply put the word “review” in your search engine along with your other topic terms to find articles of this type on the Internet or in an electronic database. The bibliography or reference section of sources you’ve already read are also excellent entry points into your own research.

Narrow your topic

There are hundreds or even thousands of articles and books on most areas of study. The narrower your topic, the easier it will be to limit the number of sources you need to read in order to get a good survey of the material. Your instructor will probably not expect you to read everything that’s out there on the topic, but you’ll make your job easier if you first limit your scope.

Keep in mind that UNC Libraries have research guides and to databases relevant to many fields of study. You can reach out to the subject librarian for a consultation: https://library.unc.edu/support/consultations/ .

And don’t forget to tap into your professor’s (or other professors’) knowledge in the field. Ask your professor questions such as: “If you had to read only one book from the 90’s on topic X, what would it be?” Questions such as this help you to find and determine quickly the most seminal pieces in the field.

Consider whether your sources are current

Some disciplines require that you use information that is as current as possible. In the sciences, for instance, treatments for medical problems are constantly changing according to the latest studies. Information even two years old could be obsolete. However, if you are writing a review in the humanities, history, or social sciences, a survey of the history of the literature may be what is needed, because what is important is how perspectives have changed through the years or within a certain time period. Try sorting through some other current bibliographies or literature reviews in the field to get a sense of what your discipline expects. You can also use this method to consider what is currently of interest to scholars in this field and what is not.

Strategies for writing the literature review

Find a focus.

A literature review, like a term paper, is usually organized around ideas, not the sources themselves as an annotated bibliography would be organized. This means that you will not just simply list your sources and go into detail about each one of them, one at a time. No. As you read widely but selectively in your topic area, consider instead what themes or issues connect your sources together. Do they present one or different solutions? Is there an aspect of the field that is missing? How well do they present the material and do they portray it according to an appropriate theory? Do they reveal a trend in the field? A raging debate? Pick one of these themes to focus the organization of your review.

Convey it to your reader

A literature review may not have a traditional thesis statement (one that makes an argument), but you do need to tell readers what to expect. Try writing a simple statement that lets the reader know what is your main organizing principle. Here are a couple of examples:

The current trend in treatment for congestive heart failure combines surgery and medicine. More and more cultural studies scholars are accepting popular media as a subject worthy of academic consideration.

Consider organization

You’ve got a focus, and you’ve stated it clearly and directly. Now what is the most effective way of presenting the information? What are the most important topics, subtopics, etc., that your review needs to include? And in what order should you present them? Develop an organization for your review at both a global and local level:

First, cover the basic categories

Just like most academic papers, literature reviews also must contain at least three basic elements: an introduction or background information section; the body of the review containing the discussion of sources; and, finally, a conclusion and/or recommendations section to end the paper. The following provides a brief description of the content of each:

• Introduction: Gives a quick idea of the topic of the literature review, such as the central theme or organizational pattern.
• Body: Contains your discussion of sources and is organized either chronologically, thematically, or methodologically (see below for more information on each).
• Conclusions/Recommendations: Discuss what you have drawn from reviewing literature so far. Where might the discussion proceed?

Organizing the body

Once you have the basic categories in place, then you must consider how you will present the sources themselves within the body of your paper. Create an organizational method to focus this section even further.

To help you come up with an overall organizational framework for your review, consider the following scenario:

You’ve decided to focus your literature review on materials dealing with sperm whales. This is because you’ve just finished reading Moby Dick, and you wonder if that whale’s portrayal is really real. You start with some articles about the physiology of sperm whales in biology journals written in the 1980’s. But these articles refer to some British biological studies performed on whales in the early 18th century. So you check those out. Then you look up a book written in 1968 with information on how sperm whales have been portrayed in other forms of art, such as in Alaskan poetry, in French painting, or on whale bone, as the whale hunters in the late 19th century used to do. This makes you wonder about American whaling methods during the time portrayed in Moby Dick, so you find some academic articles published in the last five years on how accurately Herman Melville portrayed the whaling scene in his novel.

Now consider some typical ways of organizing the sources into a review:

• Chronological: If your review follows the chronological method, you could write about the materials above according to when they were published. For instance, first you would talk about the British biological studies of the 18th century, then about Moby Dick, published in 1851, then the book on sperm whales in other art (1968), and finally the biology articles (1980s) and the recent articles on American whaling of the 19th century. But there is relatively no continuity among subjects here. And notice that even though the sources on sperm whales in other art and on American whaling are written recently, they are about other subjects/objects that were created much earlier. Thus, the review loses its chronological focus.
• By publication: Order your sources by publication chronology, then, only if the order demonstrates a more important trend. For instance, you could order a review of literature on biological studies of sperm whales if the progression revealed a change in dissection practices of the researchers who wrote and/or conducted the studies.
• By trend: A better way to organize the above sources chronologically is to examine the sources under another trend, such as the history of whaling. Then your review would have subsections according to eras within this period. For instance, the review might examine whaling from pre-1600-1699, 1700-1799, and 1800-1899. Under this method, you would combine the recent studies on American whaling in the 19th century with Moby Dick itself in the 1800-1899 category, even though the authors wrote a century apart.
• Thematic: Thematic reviews of literature are organized around a topic or issue, rather than the progression of time. However, progression of time may still be an important factor in a thematic review. For instance, the sperm whale review could focus on the development of the harpoon for whale hunting. While the study focuses on one topic, harpoon technology, it will still be organized chronologically. The only difference here between a “chronological” and a “thematic” approach is what is emphasized the most: the development of the harpoon or the harpoon technology.But more authentic thematic reviews tend to break away from chronological order. For instance, a thematic review of material on sperm whales might examine how they are portrayed as “evil” in cultural documents. The subsections might include how they are personified, how their proportions are exaggerated, and their behaviors misunderstood. A review organized in this manner would shift between time periods within each section according to the point made.
• Methodological: A methodological approach differs from the two above in that the focusing factor usually does not have to do with the content of the material. Instead, it focuses on the “methods” of the researcher or writer. For the sperm whale project, one methodological approach would be to look at cultural differences between the portrayal of whales in American, British, and French art work. Or the review might focus on the economic impact of whaling on a community. A methodological scope will influence either the types of documents in the review or the way in which these documents are discussed. Once you’ve decided on the organizational method for the body of the review, the sections you need to include in the paper should be easy to figure out. They should arise out of your organizational strategy. In other words, a chronological review would have subsections for each vital time period. A thematic review would have subtopics based upon factors that relate to the theme or issue.

Sometimes, though, you might need to add additional sections that are necessary for your study, but do not fit in the organizational strategy of the body. What other sections you include in the body is up to you. Put in only what is necessary. Here are a few other sections you might want to consider:

• Current Situation: Information necessary to understand the topic or focus of the literature review.
• History: The chronological progression of the field, the literature, or an idea that is necessary to understand the literature review, if the body of the literature review is not already a chronology.
• Methods and/or Standards: The criteria you used to select the sources in your literature review or the way in which you present your information. For instance, you might explain that your review includes only peer-reviewed articles and journals.

Questions for Further Research: What questions about the field has the review sparked? How will you further your research as a result of the review?

Begin composing

Once you’ve settled on a general pattern of organization, you’re ready to write each section. There are a few guidelines you should follow during the writing stage as well. Here is a sample paragraph from a literature review about sexism and language to illuminate the following discussion:

However, other studies have shown that even gender-neutral antecedents are more likely to produce masculine images than feminine ones (Gastil, 1990). Hamilton (1988) asked students to complete sentences that required them to fill in pronouns that agreed with gender-neutral antecedents such as “writer,” “pedestrian,” and “persons.” The students were asked to describe any image they had when writing the sentence. Hamilton found that people imagined 3.3 men to each woman in the masculine “generic” condition and 1.5 men per woman in the unbiased condition. Thus, while ambient sexism accounted for some of the masculine bias, sexist language amplified the effect. (Source: Erika Falk and Jordan Mills, “Why Sexist Language Affects Persuasion: The Role of Homophily, Intended Audience, and Offense,” Women and Language19:2).

Use evidence

In the example above, the writers refer to several other sources when making their point. A literature review in this sense is just like any other academic research paper. Your interpretation of the available sources must be backed up with evidence to show that what you are saying is valid.

Be selective

Select only the most important points in each source to highlight in the review. The type of information you choose to mention should relate directly to the review’s focus, whether it is thematic, methodological, or chronological.

Use quotes sparingly

Falk and Mills do not use any direct quotes. That is because the survey nature of the literature review does not allow for in-depth discussion or detailed quotes from the text. Some short quotes here and there are okay, though, if you want to emphasize a point, or if what the author said just cannot be rewritten in your own words. Notice that Falk and Mills do quote certain terms that were coined by the author, not common knowledge, or taken directly from the study. But if you find yourself wanting to put in more quotes, check with your instructor.

Summarize and synthesize

Remember to summarize and synthesize your sources within each paragraph as well as throughout the review. The authors here recapitulate important features of Hamilton’s study, but then synthesize it by rephrasing the study’s significance and relating it to their own work.

Keep your own voice

While the literature review presents others’ ideas, your voice (the writer’s) should remain front and center. Notice that Falk and Mills weave references to other sources into their own text, but they still maintain their own voice by starting and ending the paragraph with their own ideas and their own words. The sources support what Falk and Mills are saying.

Use caution when paraphrasing

When paraphrasing a source that is not your own, be sure to represent the author’s information or opinions accurately and in your own words. In the preceding example, Falk and Mills either directly refer in the text to the author of their source, such as Hamilton, or they provide ample notation in the text when the ideas they are mentioning are not their own, for example, Gastil’s. For more information, please see our handout on plagiarism .

Revise, revise, revise

Draft in hand? Now you’re ready to revise. Spending a lot of time revising is a wise idea, because your main objective is to present the material, not the argument. So check over your review again to make sure it follows the assignment and/or your outline. Then, just as you would for most other academic forms of writing, rewrite or rework the language of your review so that you’ve presented your information in the most concise manner possible. Be sure to use terminology familiar to your audience; get rid of unnecessary jargon or slang. Finally, double check that you’ve documented your sources and formatted the review appropriately for your discipline. For tips on the revising and editing process, see our handout on revising drafts .

Works consulted

We consulted these works while writing this handout. This is not a comprehensive list of resources on the handout’s topic, and we encourage you to do your own research to find additional publications. Please do not use this list as a model for the format of your own reference list, as it may not match the citation style you are using. For guidance on formatting citations, please see the UNC Libraries citation tutorial . We revise these tips periodically and welcome feedback.

Anson, Chris M., and Robert A. Schwegler. 2010. The Longman Handbook for Writers and Readers , 6th ed. New York: Longman.

Jones, Robert, Patrick Bizzaro, and Cynthia Selfe. 1997. The Harcourt Brace Guide to Writing in the Disciplines . New York: Harcourt Brace.

Lamb, Sandra E. 1998. How to Write It: A Complete Guide to Everything You’ll Ever Write . Berkeley: Ten Speed Press.

Rosen, Leonard J., and Laurence Behrens. 2003. The Allyn & Bacon Handbook , 5th ed. New York: Longman.

Troyka, Lynn Quittman, and Doug Hesse. 2016. Simon and Schuster Handbook for Writers , 11th ed. London: Pearson.

Make a Gift

Literature Review - what is a Literature Review, why it is important and how it is done

What are literature reviews, goals of literature reviews, types of literature reviews, about this guide/licence.

• Strategies to Find Sources
• Evaluating Literature Reviews and Sources
• Tips for Writing Literature Reviews
• Writing Literature Review: Useful Sites
• Citation Resources
• Other Academic Writings
• Useful Resources

Help is Just a Click Away

Search our FAQ Knowledge base, ask a question, chat, send comments...

Go to LibAnswers

 What is a literature review? "A literature review is an account of what has been published on a topic by accredited scholars and researchers. In writing the literature review, your purpose is to convey to your reader what knowledge and ideas have been established on a topic, and what their strengths and weaknesses are. As a piece of writing, the literature review must be defined by a guiding concept (e.g., your research objective, the problem or issue you are discussing, or your argumentative thesis). It is not just a descriptive list of the material available, or a set of summaries. " - Quote from Taylor, D. (n.d) "The literature review: A few tips on conducting it"

Source NC State University Libraries. This video is published under a Creative Commons 3.0 BY-NC-SA US license.

What are the goals of creating a Literature Review?

• To develop a theory or evaluate an existing theory
• To summarize the historical or existing state of a research topic
• Identify a problem in a field of research 

- Baumeister, R.F. & Leary, M.R. (1997). "Writing narrative literature reviews," Review of General Psychology , 1(3), 311-320.

When do you need to write a Literature Review?

• When writing a prospectus or a thesis/dissertation
• When writing a research paper
• When writing a grant proposal

In all these cases you need to dedicate a chapter in these works to showcase what have been written about your research topic and to point out how your own research will shed a new light into these body of scholarship.

Literature reviews are also written as standalone articles as a way to survey a particular research topic in-depth. This type of literature reviews look at a topic from a historical perspective to see how the understanding of the topic have change through time.

What kinds of literature reviews are written?

• Narrative Review: The purpose of this type of review is to describe the current state of the research on a specific topic/research and to offer a critical analysis of the literature reviewed. Studies are grouped by research/theoretical categories, and themes and trends, strengths and weakness, and gaps are identified. The review ends with a conclusion section which summarizes the findings regarding the state of the research of the specific study, the gaps identify and if applicable, explains how the author's research will address gaps identify in the review and expand the knowledge on the topic reviewed.
• Book review essays/ Historiographical review essays : This is a type of review that focus on a small set of research books on a particular topic " to locate these books within current scholarship, critical methodologies, and approaches" in the field. - LARR
• Systematic review : "The authors of a systematic review use a specific procedure to search the research literature, select the studies to include in their review, and critically evaluate the studies they find." (p. 139). Nelson, L.K. (2013). Research in Communication Sciences and Disorders . San Diego, CA: Plural Publishing.
• Meta-analysis : "Meta-analysis is a method of reviewing research findings in a quantitative fashion by transforming the data from individual studies into what is called an effect size and then pooling and analyzing this information. The basic goal in meta-analysis is to explain why different outcomes have occurred in different studies." (p. 197). Roberts, M.C. & Ilardi, S.S. (2003). Handbook of Research Methods in Clinical Psychology . Malden, MA: Blackwell Pub.
• Meta-synthesis : "Qualitative meta-synthesis is a type of qualitative study that uses as data the findings from other qualitative studies linked by the same or related topic." (p.312). Zimmer, L. (2006). "Qualitative meta-synthesis: A question of dialoguing with texts," Journal of Advanced Nursing , 53(3), 311-318.

Guide adapted from "Literature Review" , a guide developed by Marisol Ramos used under CC BY 4.0 /modified from original.

• Next: Strategies to Find Sources >>
• Last Updated: Nov 25, 2021 10:46 AM
• URL: https://lit.libguides.com/Literature-Review

The Library, Technological University of the Shannon: Midwest

How to Write a Literature Review

What is a literature review.

• What Is the Literature
• Writing the Review

A literature review is much more than an annotated bibliography or a list of separate reviews of articles and books. It is a critical, analytical summary and synthesis of the current knowledge of a topic. Thus it should compare and relate different theories, findings, etc, rather than just summarize them individually. In addition, it should have a particular focus or theme to organize the review. It does not have to be an exhaustive account of everything published on the topic, but it should discuss all the significant academic literature and other relevant sources important for that focus.

This is meant to be a general guide to writing a literature review: ways to structure one, what to include, how it supplements other research. For more specific help on writing a review, and especially for help on finding the literature to review, sign up for a Personal Research Session .

The specific organization of a literature review depends on the type and purpose of the review, as well as on the specific field or topic being reviewed. But in general, it is a relatively brief but thorough exploration of past and current work on a topic. Rather than a chronological listing of previous work, though, literature reviews are usually organized thematically, such as different theoretical approaches, methodologies, or specific issues or concepts involved in the topic. A thematic organization makes it much easier to examine contrasting perspectives, theoretical approaches, methodologies, findings, etc, and to analyze the strengths and weaknesses of, and point out any gaps in, previous research. And this is the heart of what a literature review is about. A literature review may offer new interpretations, theoretical approaches, or other ideas; if it is part of a research proposal or report it should demonstrate the relationship of the proposed or reported research to others' work; but whatever else it does, it must provide a critical overview of the current state of research efforts. 

Literature reviews are common and very important in the sciences and social sciences. They are less common and have a less important role in the humanities, but they do have a place, especially stand-alone reviews.

Types of Literature Reviews

There are different types of literature reviews, and different purposes for writing a review, but the most common are:

• Stand-alone literature review articles . These provide an overview and analysis of the current state of research on a topic or question. The goal is to evaluate and compare previous research on a topic to provide an analysis of what is currently known, and also to reveal controversies, weaknesses, and gaps in current work, thus pointing to directions for future research. You can find examples published in any number of academic journals, but there is a series of Annual Reviews of *Subject* which are specifically devoted to literature review articles. Writing a stand-alone review is often an effective way to get a good handle on a topic and to develop ideas for your own research program. For example, contrasting theoretical approaches or conflicting interpretations of findings can be the basis of your research project: can you find evidence supporting one interpretation against another, or can you propose an alternative interpretation that overcomes their limitations?
• Part of a research proposal . This could be a proposal for a PhD dissertation, a senior thesis, or a class project. It could also be a submission for a grant. The literature review, by pointing out the current issues and questions concerning a topic, is a crucial part of demonstrating how your proposed research will contribute to the field, and thus of convincing your thesis committee to allow you to pursue the topic of your interest or a funding agency to pay for your research efforts.
• Part of a research report . When you finish your research and write your thesis or paper to present your findings, it should include a literature review to provide the context to which your work is a contribution. Your report, in addition to detailing the methods, results, etc. of your research, should show how your work relates to others' work.

A literature review for a research report is often a revision of the review for a research proposal, which can be a revision of a stand-alone review. Each revision should be a fairly extensive revision. With the increased knowledge of and experience in the topic as you proceed, your understanding of the topic will increase. Thus, you will be in a better position to analyze and critique the literature. In addition, your focus will change as you proceed in your research. Some areas of the literature you initially reviewed will be marginal or irrelevant for your eventual research, and you will need to explore other areas more thoroughly. 

Examples of Literature Reviews

See the series of Annual Reviews of *Subject* which are specifically devoted to literature review articles to find many examples of stand-alone literature reviews in the biomedical, physical, and social sciences. 

Research report articles vary in how they are organized, but a common general structure is to have sections such as:

• Abstract - Brief summary of the contents of the article
• Introduction - A explanation of the purpose of the study, a statement of the research question(s) the study intends to address
• Literature review - A critical assessment of the work done so far on this topic, to show how the current study relates to what has already been done
• Methods - How the study was carried out (e.g. instruments or equipment, procedures, methods to gather and analyze data)
• Results - What was found in the course of the study
• Discussion - What do the results mean
• Conclusion - State the conclusions and implications of the results, and discuss how it relates to the work reviewed in the literature review; also, point to directions for further work in the area

Here are some articles that illustrate variations on this theme. There is no need to read the entire articles (unless the contents interest you); just quickly browse through to see the sections, and see how each section is introduced and what is contained in them.

The Determinants of Undergraduate Grade Point Average: The Relative Importance of Family Background, High School Resources, and Peer Group Effects , in The Journal of Human Resources , v. 34 no. 2 (Spring 1999), p. 268-293.

This article has a standard breakdown of sections:

• Introduction
• Literature Review
• Some discussion sections

First Encounters of the Bureaucratic Kind: Early Freshman Experiences with a Campus Bureaucracy , in The Journal of Higher Education , v. 67 no. 6 (Nov-Dec 1996), p. 660-691.

This one does not have a section specifically labeled as a "literature review" or "review of the literature," but the first few sections cite a long list of other sources discussing previous research in the area before the authors present their own study they are reporting.

• Next: What Is the Literature >>
• Last Updated: Mar 2, 2023 9:33 AM
• URL: https://libguides.wesleyan.edu/litreview

• University of Texas Libraries

Literature Reviews

• What is a literature review?
• Steps in the Literature Review Process
• Define your research question
• Determine inclusion and exclusion criteria
• Choose databases and search
• Review Results
• Synthesize Results
• Analyze Results
• Librarian Support

What is a Literature Review?

A literature or narrative review is a comprehensive review and analysis of the published literature on a specific topic or research question. The literature that is reviewed contains: books, articles, academic articles, conference proceedings, association papers, and dissertations. It contains the most pertinent studies and points to important past and current research and practices. It provides background and context, and shows how your research will contribute to the field. 

A literature review should: 

• Provide a comprehensive and updated review of the literature;
• Explain why this review has taken place;
• Articulate a position or hypothesis;
• Acknowledge and account for conflicting and corroborating points of view

From  S age Research Methods

Purpose of a Literature Review

A literature review can be written as an introduction to a study to:

• Demonstrate how a study fills a gap in research
• Compare a study with other research that's been done

Or it can be a separate work (a research article on its own) which:

• Organizes or describes a topic
• Describes variables within a particular issue/problem

Limitations of a Literature Review

Some of the limitations of a literature review are:

• It's a snapshot in time. Unlike other reviews, this one has beginning, a middle and an end. There may be future developments that could make your work less relevant.
• It may be too focused. Some niche studies may miss the bigger picture.
• It can be difficult to be comprehensive. There is no way to make sure all the literature on a topic was considered.
• It is easy to be biased if you stick to top tier journals. There may be other places where people are publishing exemplary research. Look to open access publications and conferences to reflect a more inclusive collection. Also, make sure to include opposing views (and not just supporting evidence).

Source: Grant, Maria J., and Andrew Booth. “A Typology of Reviews: An Analysis of 14 Review Types and Associated Methodologies.” Health Information & Libraries Journal, vol. 26, no. 2, June 2009, pp. 91–108. Wiley Online Library, doi:10.1111/j.1471-1842.2009.00848.x.

Meryl Brodsky : Communication and Information Studies

Hannah Chapman Tripp : Biology, Neuroscience

Carolyn Cunningham : Human Development & Family Sciences, Psychology, Sociology

Larayne Dallas : Engineering

Janelle Hedstrom : Special Education, Curriculum & Instruction, Ed Leadership & Policy ​

Susan Macicak : Linguistics

Imelda Vetter : Dell Medical School

For help in other subject areas, please see the guide to library specialists by subject .

Periodically, UT Libraries runs a workshop covering the basics and library support for literature reviews. While we try to offer these once per academic year, we find providing the recording to be helpful to community members who have missed the session. Following is the most recent recording of the workshop, Conducting a Literature Review. To view the recording, a UT login is required.

• October 26, 2022 recording
• Last Updated: Oct 26, 2022 2:49 PM
• URL: https://guides.lib.utexas.edu/literaturereviews

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

The Research Proposal

83 Components of the Literature Review

Krathwohl (2005) suggests and describes a variety of components to include in a research proposal.  The following sections present these components in a suggested template for you to follow in the preparation of your research proposal.

Introduction

The introduction sets the tone for what follows in your research proposal – treat it as the initial pitch of your idea.  After reading the introduction your reader should:

• Understand what it is you want to do;
• Have a sense of your passion for the topic;
• Be excited about the study´s possible outcomes.

As you begin writing your research proposal it is helpful to think of the introduction as a narrative of what it is you want to do, written in one to three paragraphs.  Within those one to three paragraphs, it is important to briefly answer the following questions:

• What is the central research problem?
• How is the topic of your research proposal related to the problem?
• What methods will you utilize to analyze the research problem?
• Why is it important to undertake this research? What is the significance of your proposed research?  Why are the outcomes of your proposed research important, and to whom or to what are they important?

Note : You may be asked by your instructor to include an abstract with your research proposal.  In such cases, an abstract should provide an overview of what it is you plan to study, your main research question, a brief explanation of your methods to answer the research question, and your expected findings. All of this information must be carefully crafted in 150 to 250 words.  A word of advice is to save the writing of your abstract until the very end of your research proposal preparation.  If you are asked to provide an abstract, you should include 5-7 key words that are of most relevance to your study. List these in order of relevance.

Background and significance

The purpose of this section is to explain the context of your proposal and to describe, in detail, why it is important to undertake this research. Assume that the person or people who will read your research proposal know nothing or very little about the research problem.  While you do not need to include all knowledge you have learned about your topic in this section, it is important to ensure that you include the most relevant material that will help to explain the goals of your research.

While there are no hard and fast rules, you should attempt to address some or all of the following key points:

• State the research problem and provide a more thorough explanation about the purpose of the study than what you stated in the introduction.
• Present the rationale for the proposed research study. Clearly indicate why this research is worth doing.  Answer the “so what?” question.
• Describe the major issues or problems to be addressed by your research. Do not forget to explain how and in what ways your proposed research builds upon previous related research.
• Explain how you plan to go about conducting your research.
• Clearly identify the key or most relevant sources of research you intend to use and explain how they will contribute to your analysis of the topic.
• Set the boundaries of your proposed research, in order to provide a clear focus. Where appropriate, state not only what you will study, but what will be excluded from your study.
• Provide clear definitions of key concepts and terms. As key concepts and terms often have numerous definitions, make sure you state which definition you will be utilizing in your research.

Literature Review

This is the most time-consuming aspect in the preparation of your research proposal and it is a key component of the research proposal. As described in Chapter 5 , the literature review provides the background to your study and demonstrates the significance of the proposed research. Specifically, it is a review and synthesis of prior research that is related to the problem you are setting forth to investigate.  Essentially, your goal in the literature review is to place your research study within the larger whole of what has been studied in the past, while demonstrating to your reader that your work is original, innovative, and adds to the larger whole.

As the literature review is information dense, it is essential that this section be intelligently structured to enable your reader to grasp the key arguments underpinning your study. However, this can be easier to state and harder to do, simply due to the fact there is usually a plethora of related research to sift through. Consequently, a good strategy for writing the literature review is to break the literature into conceptual categories or themes, rather than attempting to describe various groups of literature you reviewed.  Chapter V, “ The Literature Review ,” describes a variety of methods to help you organize the themes.

Here are some suggestions on how to approach the writing of your literature review:

• Think about what questions other researchers have asked, what methods they used, what they found, and what they recommended based upon their findings.
• Do not be afraid to challenge previous related research findings and/or conclusions.
• Assess what you believe to be missing from previous research and explain how your research fills in this gap and/or extends previous research

It is important to note that a significant challenge related to undertaking a literature review is knowing when to stop.  As such, it is important to know how to know when you have uncovered the key conceptual categories underlying your research topic.  Generally, when you start to see repetition in the conclusions or recommendations, you can have confidence that you have covered all of the significant conceptual categories in your literature review.  However, it is also important to acknowledge that researchers often find themselves returning to the literature as they collect and analyze their data.  For example, an unexpected finding may develop as one collects and/or analyzes the data and it is important to take the time to step back and review the literature again, to ensure that no other researchers have found a similar finding.  This may include looking to research outside your field.

This situation occurred with one of the authors of this textbook´s research related to community resilience.  During the interviews, the researchers heard many participants discuss individual resilience factors and how they believed these individual factors helped make the community more resilient, overall.  Sheppard and Williams (2016) had not discovered these individual factors in their original literature review on community and environmental resilience. However, when they returned to the literature to search for individual resilience factors, they discovered a small body of literature in the child and youth psychology field. Consequently, Sheppard and Williams had to go back and add a new section to their literature review on individual resilience factors. Interestingly, their research appeared to be the first research to link individual resilience factors with community resilience factors.

Research design and methods

The objective of this section of the research proposal is to convince the reader that your overall research design and methods of analysis will enable you to solve the research problem you have identified and also enable you to accurately and effectively interpret the results of your research. Consequently, it is critical that the research design and methods section is well-written, clear, and logically organized.  This demonstrates to your reader that you know what you are going to do and how you are going to do it.  Overall, you want to leave your reader feeling confident that you have what it takes to get this research study completed in a timely fashion.

Essentially, this section of the research proposal should be clearly tied to the specific objectives of your study; however, it is also important to draw upon and include examples from the literature review that relate to your design and intended methods.  In other words, you must clearly demonstrate how your study utilizes and builds upon past studies, as it relates to the research design and intended methods.  For example, what methods have been used by other researchers in similar studies?

While it is important to consider the methods that other researchers have employed, it is equally important, if not more so, to consider what methods have not been employed but could be.  Remember, the methods section is not simply a list of tasks to be undertaken. It is also an argument as to why and how the tasks you have outlined will help you investigate the research problem and answer your research question(s).

Tips for writing the research design and methods section:

• Specify the methodological approaches you intend to employ to obtain information and the techniques you will use to analyze the data.
• Specify the research operations you will undertake and he way you will interpret the results of those operations in relation to the research problem.
• Go beyond stating what you hope to achieve through the methods you have chosen. State how you will actually do the methods (i.e. coding interview text, running regression analysis, etc.).
• Anticipate and acknowledge any potential barriers you may encounter when undertaking your research and describe how you will address these barriers.
• Explain where you believe you will find challenges related to data collection, including access to participants and information.

Preliminary suppositions and implications

The purpose of this section is to argue how and in what ways you anticipate that your research will refine, revise, or extend existing knowledge in the area of your study. Depending upon the aims and objectives of your study, you should also discuss how your anticipated findings may impact future research.  For example, is it possible that your research may lead to a new policy, new theoretical understanding, or a new method for analyzing data?  How might your study influence future studies?  What might your study mean for future practitioners working in the field?  Who or what may benefit from your study?  How might your study contribute to social, economic, environmental issues?  While it is important to think about and discuss possibilities such as these, it is equally important to be realistic in stating your anticipated findings.  In other words, you do not want to delve into idle speculation.  Rather, the purpose here is to reflect upon gaps in the current body of literature and to describe how and in what ways you anticipate your research will begin to fill in some or all of those gaps.

The conclusion reiterates the importance and significance of your research proposal and it provides a brief summary of the entire proposed study.  Essentially, this section should only be one or two paragraphs in length. Here is a potential outline for your conclusion:

• Discuss why the study should be done. Specifically discuss how you expect your study will advance existing knowledge and how your study is unique.
• Explain the specific purpose of the study and the research questions that the study will answer.
• Explain why the research design and methods chosen for this study are appropriate, and why other design and methods were not chosen.
• State the potential implications you expect to emerge from your proposed study,
• Provide a sense of how your study fits within the broader scholarship currently in existence related to the research problem.

As with any scholarly research paper, you must cite the sources you used in composing your research proposal.  In a research proposal, this can take two forms: a reference list or a bibliography.  A reference list does what the name suggests, it lists the literature you referenced in the body of your research proposal.  All references in the reference list, must appear in the body of the research proposal.  Remember, it is not acceptable to say “as cited in …”  As a researcher you must always go to the original source and check it for yourself.  Many errors are made in referencing, even by top researchers, and so it is important not to perpetuate an error made by someone else. While this can be time consuming, it is the proper way to undertake a literature review.

In contrast, a bibliography , is a list of everything you used or cited in your research proposal, with additional citations to any key sources relevant to understanding the research problem.  In other words, sources cited in your bibliography may not necessarily appear in the body of your research proposal.  Make sure you check with your instructor to see which of the two you are expected to produce.

Overall, your list of citations should be a testament to the fact that you have done a sufficient level of preliminary research to ensure that your project will complement, but not duplicate, previous research efforts. For social sciences, the reference list or bibliography should be prepared in American Psychological Association (APA) referencing format. Usually, the reference list (or bibliography) is not included in the word count of the research proposal. Again, make sure you check with your instructor to confirm.

An Introduction to Research Methods in Sociology by Valerie A. Sheppard is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License , except where otherwise noted.

Share This Book

An official website of the United States government

The .gov means it’s official. Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

The site is secure. The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

• Publications
• Account settings
• Advanced Search
• Journal List
• PLoS Comput Biol
• v.9(7); 2013 Jul

Ten Simple Rules for Writing a Literature Review

Marco pautasso.

1 Centre for Functional and Evolutionary Ecology (CEFE), CNRS, Montpellier, France

2 Centre for Biodiversity Synthesis and Analysis (CESAB), FRB, Aix-en-Provence, France

Literature reviews are in great demand in most scientific fields. Their need stems from the ever-increasing output of scientific publications [1] . For example, compared to 1991, in 2008 three, eight, and forty times more papers were indexed in Web of Science on malaria, obesity, and biodiversity, respectively [2] . Given such mountains of papers, scientists cannot be expected to examine in detail every single new paper relevant to their interests [3] . Thus, it is both advantageous and necessary to rely on regular summaries of the recent literature. Although recognition for scientists mainly comes from primary research, timely literature reviews can lead to new synthetic insights and are often widely read [4] . For such summaries to be useful, however, they need to be compiled in a professional way [5] .

When starting from scratch, reviewing the literature can require a titanic amount of work. That is why researchers who have spent their career working on a certain research issue are in a perfect position to review that literature. Some graduate schools are now offering courses in reviewing the literature, given that most research students start their project by producing an overview of what has already been done on their research issue [6] . However, it is likely that most scientists have not thought in detail about how to approach and carry out a literature review.

Reviewing the literature requires the ability to juggle multiple tasks, from finding and evaluating relevant material to synthesising information from various sources, from critical thinking to paraphrasing, evaluating, and citation skills [7] . In this contribution, I share ten simple rules I learned working on about 25 literature reviews as a PhD and postdoctoral student. Ideas and insights also come from discussions with coauthors and colleagues, as well as feedback from reviewers and editors.

Rule 1: Define a Topic and Audience

How to choose which topic to review? There are so many issues in contemporary science that you could spend a lifetime of attending conferences and reading the literature just pondering what to review. On the one hand, if you take several years to choose, several other people may have had the same idea in the meantime. On the other hand, only a well-considered topic is likely to lead to a brilliant literature review [8] . The topic must at least be:

• interesting to you (ideally, you should have come across a series of recent papers related to your line of work that call for a critical summary),
• an important aspect of the field (so that many readers will be interested in the review and there will be enough material to write it), and
• a well-defined issue (otherwise you could potentially include thousands of publications, which would make the review unhelpful).

Ideas for potential reviews may come from papers providing lists of key research questions to be answered [9] , but also from serendipitous moments during desultory reading and discussions. In addition to choosing your topic, you should also select a target audience. In many cases, the topic (e.g., web services in computational biology) will automatically define an audience (e.g., computational biologists), but that same topic may also be of interest to neighbouring fields (e.g., computer science, biology, etc.).

Rule 2: Search and Re-search the Literature

After having chosen your topic and audience, start by checking the literature and downloading relevant papers. Five pieces of advice here:

• keep track of the search items you use (so that your search can be replicated [10] ),
• keep a list of papers whose pdfs you cannot access immediately (so as to retrieve them later with alternative strategies),
• use a paper management system (e.g., Mendeley, Papers, Qiqqa, Sente),
• define early in the process some criteria for exclusion of irrelevant papers (these criteria can then be described in the review to help define its scope), and
• do not just look for research papers in the area you wish to review, but also seek previous reviews.

The chances are high that someone will already have published a literature review ( Figure 1 ), if not exactly on the issue you are planning to tackle, at least on a related topic. If there are already a few or several reviews of the literature on your issue, my advice is not to give up, but to carry on with your own literature review,

The bottom-right situation (many literature reviews but few research papers) is not just a theoretical situation; it applies, for example, to the study of the impacts of climate change on plant diseases, where there appear to be more literature reviews than research studies [33] .

• discussing in your review the approaches, limitations, and conclusions of past reviews,
• trying to find a new angle that has not been covered adequately in the previous reviews, and
• incorporating new material that has inevitably accumulated since their appearance.

When searching the literature for pertinent papers and reviews, the usual rules apply:

• be thorough,
• use different keywords and database sources (e.g., DBLP, Google Scholar, ISI Proceedings, JSTOR Search, Medline, Scopus, Web of Science), and
• look at who has cited past relevant papers and book chapters.

Rule 3: Take Notes While Reading

If you read the papers first, and only afterwards start writing the review, you will need a very good memory to remember who wrote what, and what your impressions and associations were while reading each single paper. My advice is, while reading, to start writing down interesting pieces of information, insights about how to organize the review, and thoughts on what to write. This way, by the time you have read the literature you selected, you will already have a rough draft of the review.

Of course, this draft will still need much rewriting, restructuring, and rethinking to obtain a text with a coherent argument [11] , but you will have avoided the danger posed by staring at a blank document. Be careful when taking notes to use quotation marks if you are provisionally copying verbatim from the literature. It is advisable then to reformulate such quotes with your own words in the final draft. It is important to be careful in noting the references already at this stage, so as to avoid misattributions. Using referencing software from the very beginning of your endeavour will save you time.

Rule 4: Choose the Type of Review You Wish to Write

After having taken notes while reading the literature, you will have a rough idea of the amount of material available for the review. This is probably a good time to decide whether to go for a mini- or a full review. Some journals are now favouring the publication of rather short reviews focusing on the last few years, with a limit on the number of words and citations. A mini-review is not necessarily a minor review: it may well attract more attention from busy readers, although it will inevitably simplify some issues and leave out some relevant material due to space limitations. A full review will have the advantage of more freedom to cover in detail the complexities of a particular scientific development, but may then be left in the pile of the very important papers “to be read” by readers with little time to spare for major monographs.

There is probably a continuum between mini- and full reviews. The same point applies to the dichotomy of descriptive vs. integrative reviews. While descriptive reviews focus on the methodology, findings, and interpretation of each reviewed study, integrative reviews attempt to find common ideas and concepts from the reviewed material [12] . A similar distinction exists between narrative and systematic reviews: while narrative reviews are qualitative, systematic reviews attempt to test a hypothesis based on the published evidence, which is gathered using a predefined protocol to reduce bias [13] , [14] . When systematic reviews analyse quantitative results in a quantitative way, they become meta-analyses. The choice between different review types will have to be made on a case-by-case basis, depending not just on the nature of the material found and the preferences of the target journal(s), but also on the time available to write the review and the number of coauthors [15] .

Rule 5: Keep the Review Focused, but Make It of Broad Interest

Whether your plan is to write a mini- or a full review, it is good advice to keep it focused 16 , 17 . Including material just for the sake of it can easily lead to reviews that are trying to do too many things at once. The need to keep a review focused can be problematic for interdisciplinary reviews, where the aim is to bridge the gap between fields [18] . If you are writing a review on, for example, how epidemiological approaches are used in modelling the spread of ideas, you may be inclined to include material from both parent fields, epidemiology and the study of cultural diffusion. This may be necessary to some extent, but in this case a focused review would only deal in detail with those studies at the interface between epidemiology and the spread of ideas.

While focus is an important feature of a successful review, this requirement has to be balanced with the need to make the review relevant to a broad audience. This square may be circled by discussing the wider implications of the reviewed topic for other disciplines.

Rule 6: Be Critical and Consistent

Reviewing the literature is not stamp collecting. A good review does not just summarize the literature, but discusses it critically, identifies methodological problems, and points out research gaps [19] . After having read a review of the literature, a reader should have a rough idea of:

• the major achievements in the reviewed field,
• the main areas of debate, and
• the outstanding research questions.

It is challenging to achieve a successful review on all these fronts. A solution can be to involve a set of complementary coauthors: some people are excellent at mapping what has been achieved, some others are very good at identifying dark clouds on the horizon, and some have instead a knack at predicting where solutions are going to come from. If your journal club has exactly this sort of team, then you should definitely write a review of the literature! In addition to critical thinking, a literature review needs consistency, for example in the choice of passive vs. active voice and present vs. past tense.

Rule 7: Find a Logical Structure

Like a well-baked cake, a good review has a number of telling features: it is worth the reader's time, timely, systematic, well written, focused, and critical. It also needs a good structure. With reviews, the usual subdivision of research papers into introduction, methods, results, and discussion does not work or is rarely used. However, a general introduction of the context and, toward the end, a recapitulation of the main points covered and take-home messages make sense also in the case of reviews. For systematic reviews, there is a trend towards including information about how the literature was searched (database, keywords, time limits) [20] .

How can you organize the flow of the main body of the review so that the reader will be drawn into and guided through it? It is generally helpful to draw a conceptual scheme of the review, e.g., with mind-mapping techniques. Such diagrams can help recognize a logical way to order and link the various sections of a review [21] . This is the case not just at the writing stage, but also for readers if the diagram is included in the review as a figure. A careful selection of diagrams and figures relevant to the reviewed topic can be very helpful to structure the text too [22] .

Rule 8: Make Use of Feedback

Reviews of the literature are normally peer-reviewed in the same way as research papers, and rightly so [23] . As a rule, incorporating feedback from reviewers greatly helps improve a review draft. Having read the review with a fresh mind, reviewers may spot inaccuracies, inconsistencies, and ambiguities that had not been noticed by the writers due to rereading the typescript too many times. It is however advisable to reread the draft one more time before submission, as a last-minute correction of typos, leaps, and muddled sentences may enable the reviewers to focus on providing advice on the content rather than the form.

Feedback is vital to writing a good review, and should be sought from a variety of colleagues, so as to obtain a diversity of views on the draft. This may lead in some cases to conflicting views on the merits of the paper, and on how to improve it, but such a situation is better than the absence of feedback. A diversity of feedback perspectives on a literature review can help identify where the consensus view stands in the landscape of the current scientific understanding of an issue [24] .

Rule 9: Include Your Own Relevant Research, but Be Objective

In many cases, reviewers of the literature will have published studies relevant to the review they are writing. This could create a conflict of interest: how can reviewers report objectively on their own work [25] ? Some scientists may be overly enthusiastic about what they have published, and thus risk giving too much importance to their own findings in the review. However, bias could also occur in the other direction: some scientists may be unduly dismissive of their own achievements, so that they will tend to downplay their contribution (if any) to a field when reviewing it.

In general, a review of the literature should neither be a public relations brochure nor an exercise in competitive self-denial. If a reviewer is up to the job of producing a well-organized and methodical review, which flows well and provides a service to the readership, then it should be possible to be objective in reviewing one's own relevant findings. In reviews written by multiple authors, this may be achieved by assigning the review of the results of a coauthor to different coauthors.

Rule 10: Be Up-to-Date, but Do Not Forget Older Studies

Given the progressive acceleration in the publication of scientific papers, today's reviews of the literature need awareness not just of the overall direction and achievements of a field of inquiry, but also of the latest studies, so as not to become out-of-date before they have been published. Ideally, a literature review should not identify as a major research gap an issue that has just been addressed in a series of papers in press (the same applies, of course, to older, overlooked studies (“sleeping beauties” [26] )). This implies that literature reviewers would do well to keep an eye on electronic lists of papers in press, given that it can take months before these appear in scientific databases. Some reviews declare that they have scanned the literature up to a certain point in time, but given that peer review can be a rather lengthy process, a full search for newly appeared literature at the revision stage may be worthwhile. Assessing the contribution of papers that have just appeared is particularly challenging, because there is little perspective with which to gauge their significance and impact on further research and society.

Inevitably, new papers on the reviewed topic (including independently written literature reviews) will appear from all quarters after the review has been published, so that there may soon be the need for an updated review. But this is the nature of science [27] – [32] . I wish everybody good luck with writing a review of the literature.

Acknowledgments

Many thanks to M. Barbosa, K. Dehnen-Schmutz, T. Döring, D. Fontaneto, M. Garbelotto, O. Holdenrieder, M. Jeger, D. Lonsdale, A. MacLeod, P. Mills, M. Moslonka-Lefebvre, G. Stancanelli, P. Weisberg, and X. Xu for insights and discussions, and to P. Bourne, T. Matoni, and D. Smith for helpful comments on a previous draft.

Funding Statement

This work was funded by the French Foundation for Research on Biodiversity (FRB) through its Centre for Synthesis and Analysis of Biodiversity data (CESAB), as part of the NETSEED research project. The funders had no role in the preparation of the manuscript.

How to write the literature review of your research paper

Study Background & Introduction

Dr. Rishibha Sachdev

Many researchers struggle when it comes to writing literature review for their research paper. A literature review is a comprehensive overview of all the knowledge available on a specific topic till date. When you decide on a research topic, usually the first step you take in the direction of conducting research is learn more about the previous research published on the topic, and this eventually translates into literature review when you write your research paper. Literature review is one of the pillars on which your research idea stands since it provides context, relevance, and background to the research problem you are exploring.  

Types of literature review

Theoretical literature review essentially involves two steps: 

• Surveying and critically reading the existing literature: this step is commonly referred to as experimental literature review.
• Summarizing and actually penning down the gist of your review in an organized manner: this is known as theoretical review.

Literature review could be a part of a dissertation or research article and a stand-alone literature review. Let us look at this in more detail.

Literature reviews for dissertation/research article

Every research report/ thesis/research article begins with an introduction to the topic of research. This forms the literature review for the article. The main purpose of the review is to introduce the readers to the need for conducting the said research. A literature review should begin with a thorough literature search using the main keywords in relevant online databases such as Google Scholar , PubMed , etc. Once all the relevant literature has been gathered, it should be organized as follows:

• Background literature about the broad research topic to introduce the readers to the field of study.
• Recent progress on the study topic which can be organized thematically or chronologically. Ideally, separate themes should be discussed in a chronological manner to describe how research in the field has evolved over time and to highlight the progress in the field.
• The review should include a comparison and contrast of different studies. Discussing the controversial aspects helps to identify the main gaps that need to be worked upon. This is essential for defining the problem statement of the study and highlighting the significance of the research under question.
• Once a problem statement has been defined, the strengths and pitfalls of other studies that have tackled the problem statement should be discussed. This is important for outlining the need and novelty of the research.

A literature review should not be a mere recounting of all the available information. It should be a critical and analytical summary of the selected literature that guides the readers through the central theme of the research.

Does your publication goal seem near yet too far? Explore the #POWERofMORE – the boost you need to achieve all your goals Click here to know more!   

Stand-alone literature reviews

Literature reviews can also be written as stand-alone articles. These are not different from the literature review sections described above; however, they are not followed by experimental data.

They basically fall into 2 broad categories: narrative reviews and systematic reviews.

1. Narrative reviews

These are theoretical discussions of relevant information on a particular topic and its critical analysis. These are mostly qualitative in nature similar to the review sections of larger articles.

Narrative reviews are usually organized as follows:

Introduction that establishes the context of the field of research and the topic of the review

Body is normally used for describing the different themes under the main topic by dividing them into different subheadings. This section compares and contrasts published studies and identifies gaps that have not been addressed or have been unsuccessfully addressed.

Conclusions. This section differs slightly between reviews which are part of research articles and narrative reviews. The section describes the main conclusions from analysis of all the current studies and puts forth further avenues for research. This section requires critical interpretation by the author such that the review adds value to existing literature. It should bring out ideas/hypotheses that can explain any discrepancies and provide solutions to existing problems.

2. Systematic reviews

On the other hand, systematic reviews follow a well-planned methodology to qualitatively or quantitatively analyze a defined number of studies. They usually focus on a single question and have clear study objectives that are worked upon in a systematic manner. These studies are based on a well-defined strategy unlike narrative reviews. Systematic reviews and narrative reviews are organized slightly differently. The details are described below:

Introduction: Systematic reviews begin with specific research questions that are defined in terms of the samples and research outcomes to be studied.

Methods (only for systematic reviews):  These studies have a comprehensive methodology that starts by narrowing down the literature for the review. Usually, specific inclusion/exclusion criteria are set based on the research questions and databases are searched based on these criteria. Once the sample studies have been shortlisted, they are analyzed in detail.

Results: The results section for these studies involves comprehensive data analysis to determine the significance of the study outcomes. Systematic reviews can be accompanied with Meta-analysis which involves statistical analysis of the included studies to increase the power of the results.

Discussion: This section usually interprets the study data based on their weighted significance and the power of the results. The study therefore provides strengthened results that are validated by the scientific rigor of the analytical method.

Before starting to write a review, it is important to determine what kind of review you want to write and follow the appropriate style and guidelines. An effective literature review is important for the complete life cycle of a research from defining the right research goals to correctly interpreting and presenting the research results.

If you wish to learn in more depth how to conduct literature search, check out this course designed exclusively for researchers:  How to conduct an effective literature search and review .

Bonus takeaway exclusively for community members

Writing a literature review requires you to read through and collate several research articles and literature sources. This can get very confusing considering the large amount of publications that need to be organized. There is no set way to do this as it will depend on your preference for reading printed articles or online resources. If you are old school and read printed articles better, then you should create a folder with all articles organized in this way:

1. Alphabetically with the last name of the first author, or

2. Chronologically with the date of publication, or

3. Thematically with different themes organized chronologically

For the more tech-savy users, organization of literature either by year of publication or themes would be more ideal. Citing and creating a reference list in your manuscript can be done either manually or by using reference management tools like Endnote from Clarivate analytics. Endnote is an excellent way to store your research library and import it into the manuscript in the format required by the journal.

The tips and guidelines in this post should help you write your literature review with ease.

Related reading: 

• A young researcher's guide to writing a literature review
• 5 Tips to write a great literature review

References:

• Tips for effective literature searching and keeping up with new publications
• Writing a Literature Review
• Systematic literature review X narrative review
• Systematic Reviews: What is a systematic review?

Create a free account and access this bonus resource

Get Instant Access

for this article

Published on: Nov 29, 2018

• Literature Review

You're looking to give wings to your academic career and publication journey. We like that!

Why don't we give you complete access! Create a free account and get unlimited access to all resources & a vibrant researcher community.

One click sign-in with your social accounts

Sign up via email

1536 visitors saw this today and 1210 signed up.

Subscribe to Manuscript Writing

Translate your research into a publication-worthy manuscript by understanding the nuances of academic writing. Subscribe and get curated reads that will help you write an excellent manuscript.

Confirm that you would also like to sign up for free personalized email coaching for this stage.

Related Reading

How to write the background of your study

4 Step approach to writing the Introduction section of a research…

Tips for writing the perfect IMRAD manuscript

How to write the literature review of your research paper 7 min read

A young researcher's guide to writing a literature review 4 min read

Secondary research – the basics of narrative reviews, systematic reviews, and meta-analysis 6 min read

A young researcher's guide to a systematic review 6 min read

A quick guide to conducting an effective review of related literature (RRL) 5 min read

Trending Searches

• Statement of the problem
• Background of study
• Scope of the study
• Types of qualitative research
• Rationale of the study
• Concept paper
• Literature review
• Introduction in research
• Under "Editor Evaluation"
• Ethics in research

Recent Searches

• Review paper
• Responding to reviewer comments
• Predatory publishers
• Scope and delimitations
• Open access
• Plagiarism in research
• Journal selection tips
• Editor assigned
• Types of articles
• "Reject and Resubmit" status
• Decision in process
• Conflict of interest

Concept Papers in Research: Deciphering the blueprint of brilliance

Concept papers hold significant importance as a precursor to a full-fledged research proposal in academia and research. Understanding the nuances and significance of a concept paper is essential for any researcher aiming to lay a strong foundation for their investigation.

Table of Contents

What Is Concept Paper

A concept paper can be defined as a concise document which outlines the fundamental aspects of a grant proposal. It outlines the initial ideas, objectives, and theoretical framework of a proposed research project. It is usually two to three-page long overview of the proposal. However, they differ from both research proposal and original research paper in lacking a detailed plan and methodology for a specific study as in research proposal provides and exclusion of the findings and analysis of a completed research project as in an original research paper. A concept paper primarily focuses on introducing the basic idea, intended research question, and the framework that will guide the research.

Purpose of a Concept Paper

A concept paper serves as an initial document, commonly required by private organizations before a formal proposal submission. It offers a preliminary overview of a project or research’s purpose, method, and implementation. It acts as a roadmap, providing clarity and coherence in research direction. Additionally, it also acts as a tool for receiving informal input. The paper is used for internal decision-making, seeking approval from the board, and securing commitment from partners. It promotes cohesive communication and serves as a professional and respectful tool in collaboration.

These papers aid in focusing on the core objectives, theoretical underpinnings, and potential methodology of the research, enabling researchers to gain initial feedback and refine their ideas before delving into detailed research.

Key Elements of a Concept Paper

Key elements of a concept paper include the title page , background , literature review , problem statement , methodology, timeline, and references. It’s crucial for researchers seeking grants as it helps evaluators assess the relevance and feasibility of the proposed research.

Writing an effective concept paper in academic research involves understanding and incorporating essential elements:

How to Write a Concept Paper?

To ensure an effective concept paper, it’s recommended to select a compelling research topic, pose numerous research questions and incorporate data and numbers to support the project’s rationale. The document must be concise (around five pages) after tailoring the content and following the formatting requirements. Additionally, infographics and scientific illustrations can enhance the document’s impact and engagement with the audience. The steps to write a concept paper are as follows:

1. Write a Crisp Title:

Choose a clear, descriptive title that encapsulates the main idea. The title should express the paper’s content. It should serve as a preview for the reader.

2. Provide a Background Information:

Give a background information about the issue or topic. Define the key terminologies or concepts. Review existing literature to identify the gaps your concept paper aims to fill.

3. Outline Contents in the Introduction:

Introduce the concept paper with a brief overview of the problem or idea you’re addressing. Explain its significance. Identify the specific knowledge gaps your   to address and mention any contradictory theories related to your   .

4. Define a Mission Statement:

The mission statement follows a clear problem statement that defines the problem or concept that need to be addressed. Write a concise mission statement that engages your research purpose and explains why gaining the reader’s approval will benefit your field.

5. Explain the Research Aim and Objectives:

Explain why your research is important and the specific questions you aim to answer through your research. State the specific goals and objectives your concept intends to achieve. Provide a detailed explanation of your concept. What is it, how does it work, and what makes it unique?

6. Detail the Methodology:

Discuss the research methods you plan to use, such as surveys, experiments, case studies, interviews, and observations. Mention any ethical concerns related to your research.

7. Outline Proposed Methods and Potential Impact:

Provide detailed information on how you will conduct your research, including any specialized equipment or collaborations. Discuss the expected results or impacts of implementing the concept. Highlight the potential benefits, whether social, economic, or otherwise.

8. Mention the Feasibility

Discuss the resources necessary for the concept’s execution. Mention the expected duration of the research and specific milestones. Outline a proposed timeline for implementing the concept.

9. Include a Support Section:

Include a section that breaks down the project’s budget, explaining the overall cost and individual expenses to demonstrate how the allocated funds will be used.

10. Provide a Conclusion:

Summarize the key points and restate the importance of the concept. If necessary, include a call to action or next steps.

Although the structure and elements of a concept paper may vary depending on the specific requirements, you can tailor your document based on the guidelines or instructions you’ve been given.

Here are some tips to write a concept paper:

Example of a Concept Paper

Here is an example of a concept paper. Please note, this is a generalized example. Your concept paper should align with the specific requirements, guidelines, and objectives you aim to achieve in your proposal. Tailor it accordingly to the needs and context of the initiative you are proposing.

 Download Now!

Importance of a Concept Paper

Concept papers serve various fields, influencing the direction and potential of research in science, social sciences, technology, and more. They contribute to the formulation of groundbreaking studies and novel ideas that can impact societal, economic, and academic spheres.

A concept paper serves several crucial purposes in various fields:

In summary, a well-crafted concept paper is essential in outlining a clear, concise, and structured framework for new ideas or proposals. It helps in assessing the feasibility, viability, and potential impact of the concept before investing significant resources into its implementation.

Role of AI in Writing Concept Papers

The increasing use of AI, particularly generative models, has facilitated the writing process for concept papers. Responsible use involves leveraging AI to assist in ideation, organization, and language refinement while ensuring that the originality and ethical standards of research are maintained.

AI plays a significant role in aiding the creation and development of concept papers in several ways:

1. Idea Generation and Organization

AI tools can assist in brainstorming initial ideas for concept papers based on key concepts. They can help in organizing information, creating outlines, and structuring the content effectively.

2. Summarizing Research and Data Analysis

AI-powered tools can assist in conducting comprehensive literature reviews, helping writers to gather and synthesize relevant information. AI algorithms can process and analyze vast amounts of data, providing insights and statistics to support the concept presented in the paper.

3. Language and Style Enhancement

AI grammar checker tools can help writers by offering grammar, style, and tone suggestions, ensuring professionalism. It can also facilitate translation, in case a global collaboration.

4. Collaboration and Feedback

AI platforms offer collaborative features that enable multiple authors to work simultaneously on a concept paper, allowing for real-time contributions and edits.

5. Customization and Personalization

AI algorithms can provide personalized recommendations based on the specific requirements or context of the concept paper. They can assist in tailoring the concept paper according to the target audience or specific guidelines.

6. Automation and Efficiency

AI can automate certain tasks, such as citation formatting, bibliography creation, or reference checking, saving time for the writer.

7. Analytics and Prediction

AI models can predict potential outcomes or impacts based on the information provided, helping writers anticipate the possible consequences of the proposed concept.

8. Real-Time Assistance

AI-driven chat-bots can provide real-time support and answers to specific questions related to the concept paper writing process.

AI’s role in writing concept papers significantly streamlines the writing process, enhances the quality of the content, and provides valuable assistance in various stages of development, contributing to the overall effectiveness of the final document.

Concept papers serve as the stepping stone in the research journey, aiding in the crystallization of ideas and the formulation of robust research proposals. It the cornerstone for translating ideas into impactful realities. Their significance spans diverse domains, from academia to business, enabling stakeholders to evaluate, invest, and realize the potential of groundbreaking concepts.

Frequently Asked Questions

A concept paper can be defined as a concise document outlining the fundamental aspects of a grant proposal such as the initial ideas, objectives, and theoretical framework of a proposed research project.

A good concept paper should offer a clear and comprehensive overview of the proposed research. It should demonstrate a strong understanding of the subject matter and outline a structured plan for its execution.

Concept paper is important to develop and clarify ideas, develop and evaluate proposal, inviting collaboration and collecting feedback, presenting proposals for academic and research initiatives and allocating resources.

Rate this article Cancel Reply

Your email address will not be published.

Enago Academy's Most Popular

• Reporting Research

8 Effective Strategies to Write Argumentative Essays

In a bustling university town, there lived a student named Alex. Popular for creativity and…

• Language & Grammar

Language as a Bridge, Not a Barrier: ESL researchers’ path to successful research and publishing

The landscape of academic research has witnessed a remarkable shift in recent years with the…

• AI in Academia

Disclosing the Use of Generative AI: Best practices for authors in manuscript preparation

The rapid proliferation of generative and other AI-based tools in research writing has ignited an…

• Publishing Research

Setting Rationale in Research: Cracking the code for excelling at research

Knowledge and curiosity lays the foundation of scientific progress. The quest for knowledge has always…

How to Design Effective Research Questionnaires for Robust Findings

As a staple in data collection, questionnaires help uncover robust and reliable findings that can…

Sign-up to read more

Subscribe for free to get unrestricted access to all our resources on research writing and academic publishing including:

• 2000+ blog articles
• 50+ Webinars
• 10+ Expert podcasts
• 50+ Infographics
• 10+ Checklists
• Research Guides

We hate spam too. We promise to protect your privacy and never spam you.

I am looking for Editing/ Proofreading services for my manuscript Tentative date of next journal submission:

What support would you need for successful conference participation?

Peer Reviewed

What do we study when we study misinformation? A scoping review of experimental research (2016-2022)

Article metrics.

CrossRef Citations

Altmetric Score

PDF Downloads

We reviewed 555 papers published from 2016–2022 that presented misinformation to participants. We identified several trends in the literature—increasing frequency of misinformation studies over time, a wide variety of topics covered, and a significant focus on COVID-19 misinformation since 2020. We also identified several important shortcomings, including overrepresentation of samples from the United States and Europe and excessive emphasis on short-term consequences of brief, text-based misinformation. Most studies examined belief in misinformation as the primary outcome. While many researchers identified behavioural consequences of misinformation exposure as a pressing concern, we observed a lack of research directly investigating behaviour change. 

School of Applied Psychology, University College Cork, Ireland

School of Psychology, University College Dublin, Ireland

Research Question

• What populations, materials, topics, methods, and outcomes are common in published misinformation research from 2016–2022?

Essay Summary

• The goal of this review was to identify the scope of methods and measures used in assessing the impact of real-world misinformation. 
• We screened 8,469 papers published between 2016 and 2022, finding 555 papers with 759 studies where participants were presented with misinformation. 
• The vast majority of studies included samples from the United States or Europe, used brief text-based misinformation (1–2 sentences), measured belief in the misinformation as a primary outcome, and had no delay between misinformation exposure and measurement of the outcome. 
• The findings highlight certain elements of misinformation research that are currently underrepresented in the literature. In particular, we note the need for more diverse samples, measurement of behaviour change in response to misinformation, and assessment of the longer-term consequences of misinformation exposure. 
• Very few papers directly examined effects of misinformation on behaviour (1%) or behavioural intentions (10%), instead measuring proxy outcomes such as belief or attitudes. Nevertheless, many papers draw conclusions regarding the consequences of misinformation for real-world behaviour.
• We advise caution in inferring behavioural consequences unless behaviours (or behavioural intentions) are explicitly measured. 
• We recommend that policymakers reflect on the specific outcomes they hope to influence and consider whether extant evidence indicates that their efforts are likely to be successful.  

Implications

In this article, we report a scoping review of misinformation research from 2016-2022. A scoping review is a useful evidence synthesis approach that is particularly appropriate when the purpose of the review is to identify knowledge gaps or investigate research conduct across a body of literature (Munn et al., 2018). Our review investigates the methods used in misinformation research since interest in so-called “fake news” spiked in the wake of the 2016 U.S. presidential election and the Brexit referendum vote. While previous publications have reflected critically on the current focus and future pathways for the field (Camargo & Simon, 2022), here we address a simple question: what do we study when we study misinformation? We are interested in the methods, outcomes, and samples that are commonly used in misinformation research and what that might tell us about our focus and blind spots.         

Our review covers studies published from January 2016 to July 2022 and includes any studies where misinformation was presented to participants by researchers. The misinformation had to be related to real-world information (i.e., not simple eyewitness misinformation effects), and the researchers had to measure participants’ response to the misinformation as a primary outcome. As expected, we found an increase in misinformation research over time, from just three studies matching our criteria in 2016 to 312 published in 2021. As the number of studies has grown, so too has the range of topics covered. The three studies published in 2016 all assessed political misinformation, but by 2021, just 35% of studies addressed this issue, while the remainder examined other topics, including climate change, vaccines, nutrition, immigration, and more. COVID-19 became a huge focus for misinformation researchers in late 2020, and our review includes over 200 studies that used COVID-related materials. Below we discuss some implications and recommendations for the field based on our findings.

Call for increased diversity & ecological validity

It has been previously noted that the evidence base for understanding misinformation is skewed by pragmatic decisions affecting the topics that researchers choose to study. For example, Altay and colleagues (2023) argue that misinformation researchers typically focus on social media because it is methodologically convenient, and that this can give rise to the false impression that misinformation is a new phenomenon or one solely confined to the internet. Our findings highlight many other methodological conveniences that affect our understanding of misinformation relating to samples, materials, and experimental design. 

Our findings clearly show that certain populations and types of misinformation are well-represented in the literature. In particular, the majority of studies (78%) drew on samples from the United States or Europe. Though the spread of misinformation is widely recognised as a global phenomenon (Lazer, 2018), countries outside the United States and Europe are underrepresented in misinformation research. We recommend more diverse samples for future studies, as well as studies that assess interventions across multiple countries at once (e.g., Porter & Wood, 2021). Before taking action, policymakers should take note of whether claims regarding the spread of misinformation or the effectiveness of particular interventions have been tested in their jurisdictions and consider whether effects are likely to generalise to other contexts.  

There are growing concerns about large-scale disinformation campaigns and how they may threaten democracies (Nagasko, 2020; Tenove, 2020). For example, research has documented elaborate Russian disinformation campaigns reaching individuals via multiple platforms, delivery methods, and media formats (Erlich & Garner, 2023; Wilson & Starbird, 2020). Our review of the misinformation literature suggests that most studies don’t evaluate conditions that are relevant to these disinformation campaigns. Most studies present misinformation in a very brief format, comprising a single presentation of simple text. Moreover, most studies do not include a delay between presentation and measurement of the outcome. This may be due to ethical concerns, which are, of course, of crucial importance when conducting misinformation research (Greene et al., 2022). Nevertheless, this has implications for policymakers, who may draw on research that does not resemble the real-world conditions in which disinformation campaigns are likely to play out. For example, there is evidence to suggest that repeated exposure can increase the potency of misinformation (Fazio et al., 2022; Pennycook et al., 2018), and some studies have found evidence of misinformation effects strengthening over time (Murphy et al., 2021). These variables are typically studied in isolation, and we,therefore, have an incomplete understanding of how they might interact in large-scale campaigns in the real world. This means that policymakers may make assumptions about which messages are likely to influence citizens based on one or two variables—for example, a news story’s source or the political congeniality of its content—without considering the impact of other potentially interacting variables, such as the delay between information exposure and the target action (e.g., voting in an election) or the number of times an individual is likely to have seen the message. In sum, we would recommend a greater focus on ecologically valid methods to assess misinformation that is presented in multiple formats, across multiple platforms, on repeated occasions, and over a longer time interval. We also encourage future research that is responsive to public and policy-maker concerns with regard to misinformation. For example, a misinformation-related topic that is frequently covered in news media is the looming threat of deepfake technology and the dystopian future it may herald (Broinowski, 2022). However, deepfakes were very rarely examined in the studies we reviewed (nine studies in total). 

Our review contributes to a growing debate as to how we should measure the effectiveness of misinformation interventions. Some have argued that measuring discernment (the ability to distinguish true from false information) is key (Guay et al., 2023). For example, in assessing whether an intervention is effective, we should consider the effects of the intervention on belief in fake news (as most studies naturally do) but also consider effects on belief in  true  news—that is, news items that accurately describe true events. This reflects the idea that while believing and sharing misinformation can lead to obvious dangers, not believing or not sharing true information may also be costly. Interventions that encourage skepticism towards media and news sources might cause substantial harm if they undercut trust in real news, particularly as true news is so much more prevalent than fake news (Acerbi et al., 2022). In our review, less than half of the included studies presented participants with both true and false information. Of those that did present true information, just 15% reported a measure of discernment (7% of all included studies), though there was some indication that this outcome measure has been more commonly reported in recent years. We recommend that future studies consider including both true items and a measure of discernment, particularly when assessing susceptibility to fake news or evaluating an intervention. Furthermore, policymakers should consider the possibility of unintended consequences if interventions aiming to reduce belief in misinformation are employed without due consideration of their effects on trust in news more generally.   

Is misinformation likely to change our behaviour?

 Many of our most pressing social concerns related to misinformation centre on the possibility of false information inciting behaviour change—for example, that political misinformation might have a causal effect on how we decide to vote, or that health misinformation might have a causal effect in refusal of vaccination or treatment. In the current review, we found the most common outcome measure was belief in misinformation (78% of studies), followed by attitudes towards the target of the misinformation (18% of studies). While it is, of course, of interest to examine how misinformation can change beliefs and attitudes, decades of research have shown that information provision is often ineffective at meaningfully changing attitudes (Albarracin & Shavitt, 2018) and even where such an intervention is successful, attitude change is not always sufficient to induce behavioural change (Verplanken & Orbell, 2022). 

When assessing whether misinformation can affect behaviour, previous research has reported mixed results. Loomba et al. (2021) found that exposure to COVID vaccine misinformation reduced intentions to get vaccinated, but other studies have reported null or inconsistent effects (Aftab & Murphy, 2022; de Saint Laurent et al., 2022; Greene & Murphy, 2021; Guess et al., 2020). The current review highlights the small number of studies that have examined offline behavioural intentions (10% of papers reviewed) or offline behaviour itself (< 1% of studies) as an outcome of misinformation exposure. Our findings reveal a mismatch between the stated goals and methodology of research, where many papers conceive of misinformation as a substantial problem and may cite behavioural outcomes (such as vaccine refusal) as the driver of this concern, but the studies instead measure belief. We acknowledge that studying real-world effects of misinformation presents some significant challenges, both practical (we cannot follow people into the voting booth or doctor’s office) and ethical (e.g., if experimental presentation of misinformation has the potential to cause real-world harm to participants or society). Moreover, it can be exceptionally difficult to identify causal links between information exposure and complex behaviours such as voting (Aral & Eckles, 2019). Nevertheless, we recommend that where researchers have an interest in behaviour change, they should endeavour to measure that as part of their study. Where a study has only measured beliefs, attitudes, or sharing intentions, we should refrain from drawing conclusions with regard to behaviour. 

From a policy perspective, those who are concerned about misinformation, such as governments and social media companies, ought to clearly specify whether these concerns relate to beliefs or behaviour, or both. Behaviour change is not the only negative outcome that may result from exposure to misinformation—confusion and distrust in news sources are also significant outcomes that many policymakers may wish to address. We recommend that policymakers reflect on the specific outcomes they hope to influence and consider whether extant evidence indicates that their efforts are likely to be successful. For example, if the goal is to reduce belief in or sharing of misinformation, there may be ample evidence to support a particular plan of action. On the other hand, if the goal is to affect a real-world behaviour such as vaccine uptake, our review suggests that the jury is still out. Policymakers may, therefore, be best advised to lend their support to new research aiming to explicitly address the question of behaviour change in response to misinformation. Specifically, we suggest that funding should be made available by national and international funding bodies to directly evaluate the impacts of misinformation in the real world. 

Finding 1: Studies assessing the effects of misinformation on behaviour are rare.

As shown in Table 1, the most commonly recorded outcome by far was belief in the misinformation presented (78% of studies), followed by attitudes (18.31%). Online behavioural intentions, like intention to share (18.05%) or intention to like or comment on a social media post (5.01%), were more commonly measured than offline behavioural intentions (10.94%), like planning to get vaccinated. A tiny proportion of studies (1.58%) measured actual behaviour and how it may change as a result of misinformation exposure. Even then, just one study (0.13%) assessed real-world behaviour—speed of tapping keys in a lab experiment (Bastick, 2021)—all other studies assessed online behaviour such as sharing of news articles or liking social media posts. Thus, no studies in this review assessed the kind of real-world behaviour targeted by misinformation, such as vaccine uptake or voting behaviour.

Finding 2: Studies in this field  overwhelmingly use short, text-based misinformation. 

The most common format for presenting misinformation was text only (62.71% of included studies), followed by text accompanied by an image (32.41%). Use of other formats was rare; video only (1.84%), text and video (1.32%), images only (< 1%), and audio only (< 1%). 

Of the studies that used textual formats (with or without additional accompanying media), the majority (62.72%) presented between one and two sentences of text. An additional 17.50% presented misinformation in a longer paragraph (more than two sentences), 12.92% presented a page or more, and 6.86% did not specify the length of misinformation text presented.

The most frequent framing for the misinformation presented was news stories (44.27%), misinformation presented with no context (33.47%), and Facebook posts (16.47%). Other less frequent misinformation framing included Twitter posts (7.64%), other social media posts (8.04%), other types of webpages (2.11%), fact checks of news stories (1.58%), and government and public communications (0.26%). 

Very few studies presented doctored media to participants; a small number (1.19%) presented deepfake videos and 1.05% presented other forms of doctored media.

Fin ding 3: Most studies assess outcomes instantly. 

Fewer than 7% of studies reported any delay between exposure to the misinformation and the measurement of outcome ( n  = 52). While many did not specify exactly how long the delay was ( n  = 30), most were less than a week; 1–2 minutes ( n  = 4), 5–10 minutes ( n  = 4), 1 day–1 week ( n  = 13), 3 weeks ( n  = 1) and 1–6 months ( n  = 2).

Finding 4: Most participants were from the USA or Europe. 

The majority of participants sampled were from the United States (49.93%), followed by Europe (28.19%) (see Table 2). All other regions each accounted for 6% or less of the total number of participants sampled, such as East Asia (5.53%), Africa (5.27%) and the Middle East (4.74%). Furthermore, 102 studies (13.26%) did not specify from where they sampled participants.

Finding 5: COVID-19 became a major focus of misinformation research. 

Political misinformation was the most commonly studied topic until 2021, when COVID-related misinformation research became the dominant focus of the field (see Table 3 for a full breakdown of the topics included in the selected studies). Overall, experimental misinformation research is on the rise. Our review included one paper from 2016, 12 papers from 2017, 18 papers from 2018, 48 papers from 2019, 123 papers from 2020, 231 papers from 2021, and 122 papers for the first half of 2022. 

Finding 6: Most studies do not report discernment between true and false misinformation.

In total, 340 studies (45.12%) presented participants with both true and false information. Of these studies, 52 (15.29%) reported a measure of discernment based on participants’ ability to discriminate between true and false information (e.g., the difference in standardised sharing intention scores between true and false items). Across the entire review then, fewer than 7% of studies report discernment between true and false information as an outcome. There was some indication that measurement of discernment is becoming more common over time; no studies included in the review reported a measure of discernment prior to 2019, and 48 out of the 52 studies that did measure discernment were published between 2020 and 2022.

A search was conducted to identify studies that presented participants with misinformation and measured their responses (e.g., belief in misinformation) after participants were exposed to misinformation. All studies must have been published since January 2016, with an English-language version available in a peer-reviewed journal. The final search for relevant records was carried out on the 16th of July, 2022. Searches were carried out in three databases (Scopus, Web of Science, and PsychINFO) using the search terms “misinformation” OR “fake news” OR “disinformation” OR “fabricated news” OR “false news.” The search strategy, inclusion criteria, and extraction templates were preregistered at  https://osf.io/d5hrj/ . 

Inclusion criteria

There were two primary criteria for inclusion in the current scoping review. A study was eligible for inclusion if it (i) presented participants with misinformation with any potential for real-world consequences and (ii) measured participants’ responses to this misinformation (e.g., belief in the misinformation, intentions to share the misinformation) as a main outcome. 

Exclusion criteria

Studies were excluded if they presented participants with misinformation of no real-world consequence (e.g., misinformation about a simulated crime, fabricated stories about fictitious plane crashes, misinformation about fictional persons that were introduced during the course of an experiment). If the misinformation was only relevant within the narrow confines of an experiment, we considered the paper ineligible. Furthermore, studies were excluded if they presented participants with general knowledge statements (e.g., trivia statements) or if they presented participants with misleading claims that were not clearly inaccurate (e.g., a general exaggeration of the benefits of a treatment). Studies were also excluded if the misinformation was only presented in the context of a debunking message, as were studies where the misinformation was presented as a hypothetical statement (e.g., “imagine if we told you that …”, “how many people do you think believe that…”). Studies of eyewitness memory were excluded, as were any studies not published in English. Finally, opinion pieces, commentaries, systematic reviews, or observational studies were excluded.

Originally, only experimental studies were to be included in the review. However, upon screening the studies, it became apparent that distinguishing between experiments, surveys, and intervention-based research was sometimes difficult—for example, cross-sectional studies exploring individual differences in fake news susceptibility might not be classified as true experiments (as they lack control groups and measure outcomes at only one time point), but they were clearly relevant to our aims. To avoid arbitrary decisions, we decided to drop this requirement and instead included all articles that met the inclusion criteria.

Screening and selection process

The search strategy yielded a total of 18,333 records (see Figure 2 for a summary of the screening process). Curious readers may note that a Google Scholar search for the search terms listed above produces a substantially different number of hits, though the number will vary from search to search. This lack of reproducibility in Google Scholar searches is one of many reasons why Google Scholar is not recommended for use in systematic reviews, and the three databases employed here are preferred (Gusenbauer & Haddaway, 2020; also see Boeker et al., 2013; Bramer et al., 2016). Following the removal of duplicates ( n  = 9,864), a total of 8,469 records were eligible to be screened. The titles and abstracts of the 8,469 eligible records were screened by six reviewers, in pairs of two, with a seventh reviewer resolving conflicts where they arose (weighted Cohen’s κ = 0.81). A total of 7,666 records were removed at this stage, as the records did not meet the criteria of the scoping review. 

The full texts of the remaining 803 records were then screened by four reviewers in pairs of two, with conflicts resolved by discussion among the pair with the conflict (weighted Cohen’s κ = 0.68). Among the 803 records, 248 records were excluded (see Figure 2 for reasons for exclusion). Thus, there were 555 papers included for extraction, with a total of 759 studies included therein. An alphabetical list of all included articles is provided in the Appendix, and the full data file listing all included studies and their labels is available at  https://osf.io/3apkt/ .

• / Psychology

Cite this Essay

Murphy, G., de Saint Laurent, C., Reynolds, M., Aftab, O., Hegarty, K. Sun, Y. & Greene, C. M. (2023). What do we study when we study misinformation? A scoping review of experimental research (2016-2022). Harvard Kennedy School (HKS) Misinformation Review . ttps://doi.org/10.37016/mr-2020-130

Bibliography

Acerbi, A., Altay, S., & Mercier, H. (2022). Fighting misinformation or fighting for information?. Harvard Kennedy School (HKS) Misinformation Review, 3 (1). https://doi.org/10.37016/mr-2020-87

Aftab, O., & Murphy, G. (2022). A single exposure to cancer misinformation may not significantly affect related behavioural intentions. HRB Open Research, 5 (82), 82. https://doi.org/10.12688/hrbopenres.13640.1

Albarracin, D., & Shavitt, S. (2018). Attitudes and attitude change. Annual Review of Psychology, 69 , 299–327. https://psycnet.apa.org/doi/10.1146/annurev-psych-122216-011911

Altay, S., Berriche, M., & Acerbi, A. (2023). Misinformation on misinformation: Conceptual and methodological challenges.  Social Media+ Society ,  9 (1), 20563051221150412. https://doi.org/10.1177/20563051221150412

Aral, S., & Eckles, D. (2019). Protecting elections from social media manipulation. Science , 365 (6456), 858–861. https://doi.org/doi:10.1126/science.aaw8243

Bastick, Z. (2021). Would you notice if fake news changed your behavior? An experiment on the unconscious effects of disinformation.  Computers in Human Behavior ,  116 , 106633. https://doi.org/10.1016/j.chb.2020.106633

Bramer, W. M., Giustini, D., & Kramer, B. M. R. (2016). Comparing the coverage, recall, and precision of searches for 120 systematic reviews in Embase, MEDLINE, and Google Scholar: A prospective study. Systematic Reviews , 5 (1), 39. https://doi.org/10.1186/s13643-016-0215-7

Boeker, M., Vach, W., & Motschall, E. (2013). Google Scholar as replacement for systematic literature searches: good relative recall and precision are not enough. BMC Medical Research Methodology , 13 (1), 131. https://doi.org/10.1186/1471-2288-13-131

Broinowski, A. (2022). Deepfake nightmares, synthetic dreams: A review of dystopian and utopian discourses around deepfakes, and why the collapse of reality may not be imminent—yet.  Journal of Asia-Pacific Pop Culture ,  7 (1), 109–139. https://doi.org/10.5325/jasiapacipopcult.7.1.0109

Camargo, C. Q., & Simon, F. M. (2022). Mis- and disinformation studies are too big to fail: Six suggestions for the field’s future. Harvard Kennedy School (HKS) Misinformation Review , 3 (5). https://doi.org/10.37016/mr-2020-106

de Saint Laurent, C., Murphy, G., Hegarty, K., & Greene, C. M. (2022). Measuring the effects of misinformation exposure and beliefs on behavioural intentions: A COVID-19 vaccination study. Cognitive Research: Principles and Implications , 7 (1), 87. https://doi.org/10.1186/s41235-022-00437-y

Erlich, A., & Garner, C. (2023). Is pro-Kremlin disinformation effective? Evidence from Ukraine. The International Journal of Press/Politics , 28( 1), 5–28. https://doi.org/10.1177/19401612211045221

Fazio, L. K., Pillai, R. M., & Patel, D. (2022). The effects of repetition on belief in naturalistic settings.  Journal of Experimental Psychology: General, 151 (10), 2604–2613. https://doi.org/10.1037/xge0001211

Greene, C. M., de Saint Laurent, C., Murphy, G., Prike, T., Hegarty, K., & Ecker, U. K. (2022). Best practices for ethical conduct of misinformation research: A scoping review and critical commentary. European Psychologist, 28 (3), 139–150. https://doi.org/10.1027/1016-9040/a000491

Greene, C. M., & Murphy, G. (2021). Quantifying the effects of fake news on behavior: Evidence from a study of COVID-19 misinformation. Journal of Experimental Psychology: Applied , 27 (4), 773–784. https://doi.org/10.1037/xap0000371

Guay, B., Berinsky, A. J., Pennycook, G., & Rand, D. (2023). How to think about whether misinformation interventions work. Nature Human Behaviour, 7 , 1231–1233. https://doi.org/10.1038/s41562-023-01667-w

Guess, A. M., Lockett, D., Lyons, B., Montgomery, J. M., Nyhan, B., & Reifler, J. (2020). “Fake news” may have limited effects beyond increasing beliefs in false claims. Harvard Kennedy School (HKS) Misinformation Review , 1 (1). https://doi.org/10.37016/mr-2020-004

Gusenbauer, M., & Haddaway, N. R. (2020). Which academic search systems are suitable for systematic reviews or meta-analyses? Evaluating retrieval qualities of Google Scholar, PubMed, and 26 other resources. Research Synthesis Methods , 11 (2), 181–217. https://doi.org/https://doi.org/10.1002/jrsm.1378

Loomba, S., de Figueiredo, A., Piatek, S. J., de Graaf, K., & Larson, H. J. (2021). Measuring the impact of COVID-19 vaccine misinformation on vaccination intent in the UK and USA. Nature Human Behaviour , 5 (3), 337–348. https://doi.org/10.1038/s41562-021-01056-1

Munn, Z., Peters, M. D., Stern, C., Tufanaru, C., McArthur, A., & Aromataris, E. (2018). Systematic review or scoping review? Guidance for authors when choosing between a systematic or scoping review approach. BMC Medical Research Methodology , 18 . https://doi.org/10.1186/s12874-018-0611-x

Murphy, G., Lynch, L., Loftus, E., & Egan, R. (2021). Push polls increase false memories for fake new stories.  Memory ,  29 (6), 693–707. https://doi.org/10.1080/09658211.2021.1934033

Nagasako, T. (2020). Global disinformation campaigns and legal challenges. International Cybersecurity Law Review, 1 (1–2), 125–136. https://doi.org/10.1365/s43439-020-00010-7

Lazer, D. M. J., Baum, M. A., Benkler, Y., Berinsky, A. J., Greenhill, K. M., Menczer, F., Metzger, M. J., Nyhan, B., Pennycook, G., Rothschild, D., Schudson, M., Sloman, S. A., Sunstein, C. R., Thorson, E. A., Watts, D. J., & Zittrain, J. L. (2018). The science of fake news. Science , 359 (6380), 1094-1096. https://doi.org/doi:10.1126/science.aao2998

Pennycook, G., Cannon, T. D., & Rand, D. G. (2018). Prior exposure increases perceived accuracy of fake news.  Journal of Experimental Psychology: General ,  147 (12), 1865–1880. https://doi.org/10.1037/xge0000465

Porter, E., & Wood, T. J. (2021). The global effectiveness of fact-checking: Evidence from simultaneous experiments in Argentina, Nigeria, South Africa, and the United Kingdom. Proceedings of the National Academy of Sciences , 118 (37), e2104235118. https://doi.org/10.1073/pnas.2104235118

Tenove, C. (2020). Protecting democracy from disinformation: Normative threats and policy responses. The International Journal of Press/Politics , 25 (3), 517–537. https://doi.org/10.1177/1940161220918740

Verplanken, B., & Orbell, S. (2022). Attitudes, habits, and behavior change. Annual Review of Psychology , 73 , 327–352. https://doi.org/10.1146/annurev-psych-020821-011744

Wilson, T., & Starbird, K. (2020). Cross-platform disinformation campaigns: lessons learned and next steps. Harvard Kennedy School (HKS) Misinformation Review , 1 (1) . https://doi.org/10.37016/mr-2020-002

This project was funded by the Health Research Board of Ireland – COV19-2020-030. The funding body had no role in the design, interpretation, or reporting of the research.

Competing Interests

The authors declare no competing interests.

This review protocol was exempt from ethics approval.

This is an open access article distributed under the terms of the Creative Commons Attribution License , which permits unrestricted use, distribution, and reproduction in any medium, provided that the original author and source are properly credited.

Data Availability

All materials needed to replicate this study are available via the Harvard Dataverse at  https://doi.org/10.7910/DVN/X1YH6S and OSF at https://osf.io/3apkt/ .

• Open access
• Published: 08 November 2023

Childhood vaccine refusal and what to do about it: a systematic review of the ethical literature

• Kerrie Wiley 1 ,
• Maria Christou-Ergos 1 ,
• Chris Degeling 2 ,
• Rosalind McDougall 3 ,
• Penelope Robinson 1 ,
• Katie Attwell 4 ,
• Catherine Helps 1 ,
• Shevaun Drislane 4 &
• Stacy M Carter 2  

BMC Medical Ethics volume  24 , Article number:  96 ( 2023 ) Cite this article

380 Accesses

9 Altmetric

Metrics details

Parental refusal of routine childhood vaccination remains an ethically contested area. This systematic review sought to explore and characterise the normative arguments made about parental refusal of routine vaccination, with the aim of providing researchers, practitioners, and policymakers with a synthesis of current normative literature.

Nine databases covering health and ethics research were searched, and 121 publications identified for the period Jan 1998 to Mar 2022. For articles, source journals were categorised according to Australian Standard Field of Research codes, and normative content was analysed using a framework analytical approach.

Most of the articles were published in biomedical journals (34%), bioethics journals (21%), and journals that carry both classifications (20%). Two central questions dominated the literature: (1) Whether vaccine refusal is justifiable (which we labelled ‘refusal arguments’); and (2) Whether strategies for dealing with those who reject vaccines are justifiable (‘response arguments’). Refusal arguments relied on principlism, religious frameworks, the rights and obligations of parents, the rights of children, the medico-legal best interests of the child standard, and the potential to cause harm to others. Response arguments were broadly divided into arguments about policy, arguments about how individual physicians should practice regarding vaccine rejectors, and both legal precedents and ethical arguments for vaccinating children against a parent’s will. Policy arguments considered the normative significance of coercion, non-medical or conscientious objections, and possible reciprocal social efforts to offset vaccine refusal. Individual physician practice arguments covered nudging and coercive practices, patient dismissal, and the ethical and professional obligations of physicians. Most of the legal precedents discussed were from the American setting, with some from the United Kingdom.

Conclusions

This review provides a comprehensive picture of the scope and substance of normative arguments about vaccine refusal and responses to vaccine refusal. It can serve as a platform for future research to extend the current normative literature, better understand the role of cultural context in normative judgements about vaccination, and more comprehensively translate the nuance of ethical arguments into practice and policy.

Peer Review reports

Introduction

Vaccine rejection has existed for as long as vaccines [ 1 ]. Despite the significant contribution of childhood vaccination to reductions in global child morbidity and mortality [ 2 ], some parents continue to reject vaccines for their children. Parents’ reasons for rejection vary widely, and often depend on their social settings. For example, in high-income settings where around 2–3% of parents reject routine childhood vaccines [ 3 , 4 ], reasons can include previous bad experiences with vaccines or the medical system, concerns about vaccine safety, doubt about the effectiveness or necessity of vaccines, alternative health approaches, and participation in particular social groups or communities. These reasons can be grounded in deeply held religious beliefs or general philosophical approaches to health, views on freedom of choice, or mistrust in government and/or the vested interests of vaccine producers, among other things [ 5 , 6 , 7 , 8 ].

Vaccination plays a dual role in disease prevention: it serves to protect the vaccinated individual from disease, and when vaccination rates reach a high enough threshold for some diseases, also protects the broader community—including those who remain unvaccinated—by disrupting disease transmission through herd immunity. This dual role of vaccination, providing benefit to both the individual and community, complicates ethical questions regarding vaccine refusal, specifically, whether vaccine rejection is ethically justifiable.

Health care providers, communities, and governments encourage uptake and discourage vaccine rejection by various means, and the dual role of vaccination is also relevant to an evaluation of these practice and policy responses. Vaccine acceptance is encouraged with interventions like incentives, health provider recommendations and “nudges” directed at individual families, as well as by facilitating easier access to vaccination through strategies such as cost reduction and making clinic locations and opening times convenient, with many of these interventions supported by varying levels of evidence [ 9 ]. Governments often discourage vaccine rejection via the imposition of mandates that can vary in type and severity [ 10 ] and are not always well-supported by evidence [ 11 ]. These can include punitive measures, such as limiting unvaccinated children’s access to early childhood education or daycare. A thorough understanding of the ethical dimensions of childhood vaccine rejection and responses to it is important when navigating vaccine rejection in the clinical setting, and when formulating policy [ 12 ]. Systematic reviews of the evidence are considered best practice for informing vaccine practice and policy however, to our knowledge there have not yet been any published systematic reviews of the literature on the ethics of childhood vaccine rejection despite there being a broad literature on the subject. We sought to systematically explore and characterise the normative arguments made about parental refusal of routine vaccination, with the aim of better informing vaccine policy and practice.

We searched nine databases for literature that discussed normative positions on childhood vaccine rejection. Refer to the PRISMA flow chart (Fig.  1 .)

PRIMSA Flow Diagram of Review

Search strategy

We searched Medline, Embase, Philosophers Index, Philpapers, Project Muse, Cinahl, The Global Digital Library on Ethics (globethics.net), The Bioethics Literature Database (BELIT), and Pubmed using the general search strategy listed in Fig.  2 for articles published between January 1998 and March 2022.

Inclusion criteria

We included any publication which provided a substantive normative argument about parental refusal of routine vaccines for children aged five and under. We used a broad definition of ‘normative’ to mark anything that goes beyond mere description to consider right and wrong, good and bad, justifiable and unjustifiable, or legitimate and illegitimate actions or ways of being in the world. Our broad conception included textual forms such as ethical reflections, prudential and legal norms, and accounts of rationality. We used ’substantive’ to mark publications where the authors’ main purpose was to make an argument about whether vaccine refusal is morally justifiable. This included empirical research that explicitly examined normative dimensions of vaccine refusal. We were limited to reviewing publications published in English.

Exclusion criteria

We excluded publications where authors made a normative claim in passing, but the publication’s main purpose was to report non-normative empirical findings. We also excluded: publications on adult vaccination (including COVID vaccination) and the HPV vaccine (which is administered in adolescence, not childhood); empirical research such as surveys or interviews, unless they expressly explored normative arguments; and descriptive publications about the characteristics of the anti-vaccination movement that provided no normative position.

Screening and data extraction

After search execution and duplicate removal, a screening triangulation exercise was undertaken to ensure consistency among the screeners. A set of 20 titles and abstracts were independently screened by six authors, and the results compared. The inclusion and exclusion criteria were refined in a subsequent group discussion, and a sub-set of full text articles were then screened and evaluated by the same group of people, and results again compared. A discussion of this second triangulation step resulted in a refined and standardized screening approach.

The authorship group were then divided into four pairs, and the remaining titles and abstracts divided among the pairs. Each individual screened titles and abstracts against inclusion criteria, and then met with their screening partner to compare results and discuss and resolve any differences.

Full text was sought for each record screened for inclusion, and a second screening then removed articles which didn’t meet the inclusion criteria once the full text was read, articles that could not be sourced, and duplicates not identified in the initial screening.

The final list of full text publications was then divided among four authors (SC, RM, CD and KW) for data extraction using the concept of “information units” described by Mertz and colleagues [ 13 ]. In this context an information unit was defined as a normative issue or argument, and each of the four ‘extracting’ authors summarized each of the relevant information units in the papers they were assigned.

For included journal articles, Australian Standard Field of Research (FoR) codes for the journal that each article appeared in were sourced as a proxy for the disciplinary location of the article (e.g. bioethics, medicine, law). We used the Australian and New Zealand Standard Research Classification (ANZSRC) 2008, as this was the current standard when analysis commenced [ 14 ]. We used two digit FoR codes (division codes) to identify the source journal as either being Medical and Health Sciences (code 11), Ethics and Philosophy (code 22) Law (code 18) or other codes grouped as “other”. In some cases, the journal was assigned a combination of these codes (refer to Fig.  3 ).

Respective percentages of included articles falling under various ANZSRC FoR Codes (2008)

Quality assessment in systematic reviews of normative literature remains a contested area, with various options and no established best practice approach [ 15 ]. In this review, we took a satisficing approach to quality appraisal [ 16 ]: publication in a peer-reviewed journal or by a reputable academic publisher was taken as a sufficient level of quality to justify inclusion in the review. The peer review process undergone by PhD theses was also taken to be a sufficient indictor of quality to justify inclusion. Further quality appraisal of individual publications was not undertaken. This aligns with the purpose of the review which was to map and synthesize the current literature on this topic.

A framework approach was used to organise and synthesise the data [ 17 ]. The extracted information units were read by one author (KW), and a coding frame inductively developed to summarise and classify the information units extracted by the group. The publications were then independently coded according to this framework by two authors (KW and PR). Following this, the two authors met and compared their coding, discussing any differences and resolving them by consensus. The data were then synthesized into themes. In addition, for journal articles, the ANZSRC Field of Research codes for the journal each article appeared in were descriptively analysed to assess the distribution of the included literature across various disciplines.

Search results

Five thousand, two hundred and thirty-one publications were returned by the searches (see Fig.  1 ). Eight hundred and twenty-two duplicates were removed in the first instance, leaving 4409 records to be screened by title and abstract. During this screening process 4058 records were excluded, leaving 351 full text publications to be assessed. Of these a further 230 records were excluded (due to not meeting the inclusion criteria, previously unidentified duplicates, or inability to source the full text), leaving 121 publications for inclusion in the review. These included 117 journal articles, three theses and one book.

Literature source type

Analysis of the ANZSRC Field of Research codes of the source journals of included articles revealed three main areas, or a combination of them (Fig.  3 ). Around half were coded to medicine (63%); of these, just over half were dual coded to ethics (20%) or another code (9%). 21% of articles were from the philosophy or ethics literature alone; another 25% were from ethics and medicine or ethics and law. Law was the least dominant discipline, with only 12% of articles being coded to law (alone or in combination with other disciplines). This pattern suggests active concern within medicine regarding non-vaccination, but also widespread overlap in concern between medicine, ethics, and law.

Main themes found in the literature

Articles addressed two central questions (see Table  1 ):

Whether vaccine refusal was justified (henceforth ‘refusal’ arguments).

Whether various policy or practice responses to those who reject vaccines are justified (henceforth ‘response’ arguments).

Descriptive analysis of content

The literature was dominated by papers focused on ‘response’ arguments (61%). A smaller group of papers address ‘refusal’ arguments (19%), and about 18% considered both ‘refusal’ and ‘response’, usually making normative arguments about vaccine refusal as background to arguments regarding ‘response’ (See Fig.  4 ). Less than 2% of papers had a different focus.

Comparative frequencies of themes occurring among included articles

‘Response’ arguments were more common in the medical and health sciences literature (ERA FoR code 11, see Fig.  5 ). Although the ethics/philosophy (FoR code 22) and law literatures (FoR code 18) were also dominated by ‘response’ arguments, these journals—unlike medical journals—were more likely to include ‘refusal’ arguments.

Comparative frequency of overarching themes across the different disciplines of the included articles

As would be expected, authors made ‘response’ and ‘refusal’ arguments in different ways. In the following sections we consider the detail of how arguments were made. We refer to each included article by its unique reference listed in Table  1 .

‘Refusal’ arguments: whether or not vaccine rejection by individual parents is justifiable

Arguments about whether vaccine refusal by individual parents is justifiable included consideration of parents’ rights, the interests of the child (including the legal ‘best interests of the child standard’), the value of herd immunity, the epistemic basis for ethical claims, and the relevance of religious views. Our sampling period included a special issue of Narrative Inquiry in Bioethics which published narratives written by parents to communicate their normative positions on vaccination. Most of these were written by non-vaccinating parents, and they make up over one third of all arguments in the identified literature that support refusal. On balance, most of the literature argues that it is not justifiable for parents to refuse routine vaccination for their children.

Some arguments within the literature were absolute in their position on whether vaccine rejection is justifiable; others weighed competing values in a situation-specific approach. Irrespective of the arguments used to justify a position, most of the literature frames the question of whether vaccine rejection is justifiable based on three key areas of concern: (i) Respect for autonomy, the doctrine of informed consent and the value of liberty, (ii) Consequences for the child and others, and/or (iii) The normative significance of parental trust, distrust, and uncertainty. We explore the main arguments within these concepts below. As the discussion shows, these concepts are not discrete – they are often weighed against one another, linked by causal claims, or held in tension in the arguments made. Figure  6 represents proportionally the ’refusal’ arguments made in the reviewed literature.

‘Refusal’ arguments made in the literature on the ethics of vaccine refusal

Respect for autonomy, the doctrine of informed consent and the value of liberty

Fifteen papers from this sample present arguments that vaccine refusal is justified based on respect for parental autonomy, rights, or liberties (21, 23, 25, 31, 32, 35, 36, 39, 68, 71, 75, 80, 94, 100, 121). Some argue that vaccine refusal is justified on the basis of preserving legal rights (31, 80) or expression of religious freedom [ 23 ]. Opposing positions (including from four of the authors who also offer arguments justifying refusal) argue that, on balance, considerations regarding respect for autonomy are, or can be, outweighed by the potential harm caused to the child and others by not vaccinating though the increased risk of vaccine preventable diseases (21, 36, 20, 23, 110). This includes legal perspectives arguing that the freedom to choose is not unfettered [ 25 ] and that courts can override parental autonomy if this is in the child’s best interest (75, 85), as well as arguments from religious perspectives that the freedom to exercise religious beliefs needs to be weighed against harm caused to others (21,91). Those who argue that vaccine refusal is justified counter that disrespecting parental autonomy can also cause harm to the child through loss of trust and possible disengagement of the child from the healthcare system (100), and that the increased risk of disease is a price worth paying to ensure that political values are preserved (71). Of note: non-vaccinating parents also assert a right to make choices for their children in support of their refusal [ 14 , 18 ], but unlike others, their arguments are based primarily on epistemic claims about vaccine effectiveness, necessity and safety rather than moral or ethical positions. However, they assert that these doubts necessitate respect for their decision.

Consequences for others and the child

Most of the literature argues for or against the justifiability of vaccine refusal based on consequences. These include potential harms from vaccine preventable diseases or vaccines themselves, or conversely, potential benefits from herd immunity. The concept of herd immunity is deployed in different ways. Those justifying vaccine refusal in certain circumstances argue that in settings where there is a high level of herd immunity, the risk posed by an unvaccinated child is not great enough to override respect for parental autonomy (62, 65, 94, 98), and that the benefits of community protection do not justify the individual risk posed by the vaccine and borne by the child who is already protected through herd immunity (72, 96, 97, 17, 93, 108). Perspectives of non-vaccinators echo these ideas by asserting that some diseases are not harmful enough to proscribe vaccine refusal [ 14 ] and that vaccine injury contributes to and justifies refusal [ 16 ].

In contrast, those who argue that refusal is not justifiable propose a duty to contribute to herd immunity because it is a public good (7,80, 19,120, 33, 48, 68,115), or that free-riding (allowing one’s child to enjoy the benefits of herd immunity provided by others, while avoiding the risk of vaccinating) is unfair (37,46, 48). On this account, the vaccine refusal of a few may undermine herd immunity and thus cause harm to the many by increasing disease risks (9, 11, 26, 37, 59, 76, 81, 86); further, these risks are borne by the most vulnerable (43). These arguments about harm to others include those made by authors writing from religious perspectives (8, 81, 84, 92, 98). Finally, an account by a vaccinating parent suggests that harms resulting from non-vaccination are blameworthy because they are an intentional act of aggression against vaccinated children [ 19 ].

The concept of the child’s interests arises frequently in these publications. Pursuing or protecting these interests generally combines concern about the consequences of non-vaccination for the child with concern for autonomy, in the broad sense of being able to direct one’s life in accordance with one’s values or aims. Authors write about the interests of the child in both a general sense (i.e. the interests of the child outside of a legal context) and in a legal sense (the formal ‘best interests of the child standard’). The legal construction is used both to support (31, 6, 93) and to oppose vaccine refusal. Arguments that receiving a vaccine is in the legal ‘best interests of the child’ (21,39) posit that any deviation from a widely accepted legal view of the interests of a child should weigh the risk of harm to the child (68) irrespective of the parent’s beliefs (78), or that non-vaccination constitutes negligence or child endangerment [ 28 ]. On the other hand, some authors argue that, from a legal perspective, parents have the right to consent to or refuse vaccination ostensibly using the ‘child’s best interests standard’(93) and that there is insufficient legal precedent to argue that non-vaccination constitutes medical neglect [ 6 ].

Arguing from distrust and uncertainty

As previously noted, the sample included a set of papers written from the perspective of non-vaccinating parents. Most of these contributions seek to justify vaccine refusal, and many justifications were grounded in distrust. They call into question vaccine safety and effectiveness [ 12 , 13 , 14 , 18 ], and the accuracy of the reporting of adverse events following immunization (96). They claim financial conflicts, constructing clinicians, clinical medicine, and/or regulatory agencies as untrustworthy or non-credible [ 12 , 14 , 16 ]. They cite empirical studies of non-vaccinators to support parental preferences for natural infection over a vaccine (97). Non-vaccinating parents were not the only authors to make arguments in this vein. Some other authors cite the lack of absolute certainty of vaccine safety as justification for parents refusing vaccines in the interests of their children (28,76), especially regarding newer vaccines for which efficacy is not well-established (34). This line of argument depicts vaccine proponents as driven by commercial interests, thus justifying parental mistrust and refusal (34). Contra this, one paper asserts that refusal on the grounds of mistrust of government or medicine is not justifiable, as it is inconsistent with the scientific evidence and the well-established regulatory processes in place, such as the rigorous clinical testing required to develop and approve vaccines, and the systems established to report adverse events and ensure safety [ 8 ].

‘Response’ arguments: claims regarding the justifiability of different responses to non-vaccination

The literature examines four main responses to non-vaccination (i) government mandate policies (such as legal ramifications for refusing vaccination and vaccination as a school entry requirement), and other coercive policies, (ii) exemptions to mandate policies, (iii) individual practitioner and medical practice responses (including patient dismissal from practice for vaccine refusal, vaccinating against parents’ will, and nudging), and (iv) withholding health resources. The literature includes authors who argue that these responses are justifiable and others who argue that they are not. Much like the refusal arguments, some response arguments are absolute in their position, while others advocate weighing competing values in a context -specific way. Like refusal arguments, most arguments for and against particular responses to non-vaccinating parents draw from respect for autonomy, the doctrine of informed consent and the value of liberty, as well as considering consequences for the child and others. Other concepts appearing in these arguments include inequity, and the duties of governments and practitioners. Figure  7 represents proportionally the ’response’ arguments made in the reviewed literature.

‘Response’ arguments made in the literature on the ethics of vaccine refusal

As in the literature on refusal, many arguments about policy or practice responses to non-vaccinating parents depend on the interrelated concepts of respect for autonomy, informed consent and liberty. Five papers engage with the issue of practitioners vaccinating against parents’ will with respect to these concepts. They argue that forced vaccination by healthcare providers violates parents’ autonomy and/or the ethical requirement for informed consent, because vaccination carries risks (80,119), and clinicians have legal obligations to obtain valid consent for procedures (94). Some authors propose alternatives to forced vaccination, including focusing on rebuilding trust (rather than violating negative liberty) (32), and accepting that views on vaccination derive from plural and culturally-specific values [ 29 ]. On the other hand, proponents of forced vaccination do not engage with these concepts, instead deploying the harm principle and the legal ‘best interests of the child standard’ to justify their position. We explore this argument in the following section “Consequences for the child and others”.

Another set of papers make arguments about vaccine mandates that also draw on autonomy or liberty justifications, often weighing these against harm or risk of harm. Arguments justifying mandates are often legal in nature and use, for example, the harm principle or case law to argue that the freedom or liberty to choose not to vaccinate is limited by the risk of ill health and/or death to the child or others in the community, including vulnerable persons (83,91). One author argues that legal actions should be brought against those who harm others by refusing vaccination, as this would both discourage refusal and, in the case of any successful claims, compensate victims (55). Some authors argue that mandates are justifiable if the exercise of liberty rights poses a threat to public health (53,82,83,91,119). While those arguing that mandates are not justifiable sometimes rely on arguments about risk of harm—i.e. that in a low-incidence (and therefore low-risk) setting mandates cannot be justified (45, 87,104)—most make their arguments from autonomy, informed consent, and personal liberty and do not weigh these against the potential for harm (12,16,61,82,89,107,114). One author argues that even if mandates improve vaccination rates, they damage trust with parents and make refusers more steadfast in their decision (121), so are not sustainable. Finally, some authors present middle-ground positions that—in their view—are more autonomy- or liberty-preserving, including persuasion (121) or weakly enforced mandates (71), or argue that policy responses should take the least coercive approach that is feasible and effective to balance the needs of the individual with public health (117).

Those supporting conscientious objection to mandates argue that such provisions contribute to the collective good of a culture of respect for autonomy (82), or reflect the “American ideal” of personal freedom (66). Contra this, those opposed to conscientious objection provisions argue that challenges to mandates based in religious freedom have failed in case law, as the right to practice religion freely does not include the liberty to expose children or communities to disease (20,92). One author provides a qualified view of conscientious objection on religious grounds, arguing that such liberties could be justified only while high vaccination rates are maintained (109).

Authors disagree about whether certain policy or practice responses do, or do not, respect autonomy or uphold important liberties. For example, authors disagree on the effect of both nudges and conscientious objection policies on parental autonomy or liberty. With respect to nudges, some argue they are autonomy-preserving because they steer parents in a certain direction while allowing choice (106), do not override or challenge the strong views of deeply opposed opponents (42, 44) and uphold informed consent (121). Some supporters of nudging weigh multiple normative considerations, arguing that nudges that appeal to social responsibilities in a medical practice setting are justified because they appropriately balance parental autonomy against the practitioner’s responsibility to promote trust and collective benefits (3,80). Those opposed to nudges for vaccination decisions argue that the invasive nature of immunization increases the need for independent and informed decision making (60,113). These authors argue against a presumptive consultation style in general practice, proposing participatory clinical encounters (114), and using persuasion (42), as alternatives to more coercive approaches.

Consequences for the child and others

Many of the arguments in this literature consider individual and collective consequences—benefits, harms, burdens, and costs to society — and propose that these may override other normative considerations. The risk and prevention of harm is particularly pertinent here. For example, a parental decision can be overruled in cases where there is a significant risk of harm to the child (78), or nudges become more justifiable when the risk of harm to others is higher (3, 75).

Arguments about mandates often include concern about consequences, since it is inherent in a vaccine mandate that there will be some costs associated with non-vaccination. Mandate proponents argue that mandates ensure high vaccination rates, thus preventing disease outbreaks (39) and associated harms (97), so are in the best interest of individual children (28, 73, 111) and serve the greater good (4,28,73,79). Some justify mandates by proposing a duty to contribute to herd immunity, including under the “clean hands principle”, that is, an obligation not to participate in collectively harmful activities [ 1 , 5 ]. Conversely, some authors argue that mandates are not necessary to achieve high levels of population immunity, so state coercion is unjustified at a collective level or at the level of the individual child because each child receives limited benefit (94). Those opposing mandates also argue that vaccine safety is not absolute (88) and that mandates are a disutility, carrying associated costs with surveillance and enforcement (95). Other authors sought to balance these kinds of consequences against other normative considerations with respect to mandates, including the level of herd immunity, the risks of non-vaccination to the child and/or society, and respect for parental autonomy (32,53,88,119). One author argues that mandates protect ‘victims’ of the anti-vaccination movement from harms so long as certain conditions are met (43): that the vaccine can prevent infection and transmission, that individuals minimize their risk of exposure, and that the right of self-defense is preserved (e.g. in the case of allergy to vaccines).

Consequences are also important to arguments about conscientious objection, but here it is generally concerns about the impact on the collective. Some argue that exemptions should not be allowed because they may increase rates of disease or undermine individual or community health (20, 87, 118); others argue that if disease risk is low, exemptions are justified because those few individuals with exemptions do not pose a risk to others or herd immunity (20, 82, 105).

Consequences to the child and others are used to justify whether responses should be applied in general practice settings. As mentioned in the previous section, some authors justify healthcare workers vaccinating against a parent’s will using both the harm principle (69) and the legal ‘best interests of the child standard’ [ 25 ]; others suggest it is against the legal best interests of an older child to be forcibly vaccinated, as this may have a more detrimental impact than being unvaccinated (25,51). The best interests of the child are also invoked extensively to argue that non-vaccinating families should not be dismissed from medical practices (98,104, 26, 75). Here authors note that an unvaccinated child is more vulnerable to vaccine preventable diseases (9, 49), practice dismissal limits opportunities to access health care (31,52, 56,79,116) and the increased risk of harm from vaccine preventable diseases is transferred to other practices (9,47,49). One paper makes an argument about the consequences of treating non-vaccinating families for general practitioners, suggesting that practices caring for unvaccinated children should disclose this to other patients to minimize medicolegal risks, and should receive legal protection to account for the increased liability and risk of caring for these patients (40).

A small body of literature employs claims about who is responsible for the consequences of non-vaccination to make arguments about responses to non-vaccination. For example, one article seeks to justify discriminating against unvaccinated children with a vaccine preventable disease by limiting their access to health resources, relying on precedents such as coronary bypass surgery being withheld from obese people and smokers, and arguing that those who contribute to their own ill-health (in this case by not vaccinating) do not deserve healthcare (80). A related argument focuses on managing refugee camps during outbreaks that pose a direct and imminent threat of harm, proposing that the state is justified in withholding humanitarian aid from non-vaccinating refugees because the state is responsible for setting conditions that provide protection to (or prevent harm to) aid givers and public health [ 30 ].

Some critiques of policy or practice responses to non-vaccination emphasise that these responses can have inequitable effects and argue that this is unjustifiable. Exemption policies are a key focus here. Five papers argue against exemptions to vaccine mandates on the grounds that these unevenly distribute the risks and benefits of vaccinations (27,61,66, 73,118). These authors propose that the inaction of a few compromises the health of the most vulnerable community members (118) and disenfranchises those with medical contraindications for vaccines [ 27 ]. One author particularly focuses on home-schooled children, arguing that exempting them from vaccine mandates exposes both those children and society to harm, and that it is in the interests of these children and society that they be protected through vaccination (73). Some authors suggest that policy exemptions could be made justifiable by imposing conditions that offset potential inequities. On this view, exemptions could be justified so long as the refuser is prepared to make a financial or other contribution to help offset the potential financial burden of the diseases they may cause, or to otherwise contribute to social good [ 2 , 22 ].

Similarly, some opponents of coercive mandates or practice dismissal for non-vaccination critique these responses for having inequitable effects. It is argued that coercion risks creating a group of disenfranchised people (113) and that different people have different capacities to resist coercive policies (114). Similarly, dismissal leaves vulnerable children without advocacy (64), leads to patients not being treated equally (63) and marginalizes children from health care (74). One paper argues that family dismissal should be strongly discouraged, and an alternative mutually beneficial solution sought after considering the interests of the patient, physician, family, community, and society at large (74).

The duty of practitioners and the state

Some papers address the duties of practitioners and the duties of the state to respond to non-vaccination, in ways that go beyond simply weighing up consequences, implications for autonomy or freedom, or equity of impacts.

A variety of duties of practitioners are proposed. The first of these is to protect a child from their parent’s beliefs if those beliefs are likely to cause significant harm, which is used to justify initiating child protection proceedings to vaccinate against a parent’s will (67). Another is to protect patients in the waiting room from the risks posed by non-vaccinating patients, which is used to justify dismissing non-vaccinating patients from practice (9,26,38, 40,45). Counter-obligations are used to argue against practice dismissal. These include a health professional’s obligation to provide healthcare in the best interest of the child despite the parent’s decisions, and to deal with infectious disease as a part of their role (9,26,45,47, 56,101). Authors also argue that physicians’ obligations exclude enforcing parental accountability through dismissal, especially if that means the child is held accountable for the actions of their parents (47), and that continuing to provide care to a non-vaccinating family does not make the physician complicit in their decision (116).

It is sometimes asserted that the state is obliged to discourage non-vaccination on a number of grounds. This includes a fundamental duty of states to protect society [ 21 ], a responsibility of states to protect herd immunity as a common good or to reduce social and financial burdens and costs (53,119), and the state’s role to protect the common good in the face of risks to public health and the fallibility of individuals’ risk perception (54). Some of these arguments focus on exemptions from mandatory vaccination policies, proposing that states can not justify such exemptions because the government’s interest in protecting society outweighs the individual’s interest [ 21 ] or because vaccination is a social and moral good owed by a society to its children (118).

This review systematically explored and characterised the normative arguments made about parental refusal of routine childhood vaccination. Included publications addressed two types of arguments (i) ‘Refusal’ arguments (whether vaccine refusal is justified) and (ii) ‘Response’ arguments (whether various policy or practice responses to those who reject vaccines are justified). There were more ‘response’ arguments than ‘refusal’ arguments in the literature. On balance, most of the literature on ‘refusal’ arguments contended that it is not justifiable for parents to refuse vaccination for their children. Most of the ‘response’ argument literature argued against the various responses to non-vaccination put forward. However, compared to ‘refusal’ arguments, ‘response’ arguments were more varied and nuanced, and often came with caveats (e.g. exemptions to mandates are permissible if the disease burden is low).

The included articles predominantly originated from medical journals: these accounted for most of the papers focused on ‘response’ arguments. This may arise from the broader distribution of academic literature – there are more papers published in medicine than in the other disciplines represented in this review. It may also reflect the needs of readers of medical literature for guidance on how they should respond to non-vaccinating parents, highlighting the importance of making literature addressing the ethical dimensions of vaccine refusal accessible to immunization practitioners. Although there were some interdisciplinary perspectives, the dominance of the medical literature relating to ‘response’ arguments suggests that knowledge in this field may be advanced by incorporating more voices with expertise in ethics, law, and policy. This is especially important for deciding how to implement policy and practice responses to non-vaccination.

‘Refusal’ arguments were more common in the comparatively smaller collection of ethics/philosophy literature identified by this search, which may be, in part, a product of the differences in disciplinary traditions. While ethics/philosophy texts explore counterarguments and reach conclusions that are nuanced, and often with caveats, medical disciplines are primarily guided by practical considerations and a tradition of arguing from evidence rather than from ethical or philosophical principles. This privileging of evidence over principles may make it difficult to explore differing vaccination positions within the medical arena, potentially contributing to the adversarial clinical immunisation encounters described by vaccine-refusing parents and clinicians alike [ 7 , 18 , 19 ]. This pattern needs attention if ethical arguments are to have an impact in practice. As shown, most ethical arguments pay attention to evidence, as most ethical arguments include consequences in some way (see below). Ethical arguments can add nuance to biomedical thinking about consequences (e.g. consequences for individuals vs. the collective) and also about competing values (e.g. balancing consequences against concerns regarding autonomy, consent and liberty). The challenge for ethicists is to provide these arguments in an accessible and compelling form.

In fact, (i) consequences for the child and others, and (ii) respect for autonomy, the doctrine of informed consent and the value of liberty were dominant themes in both ‘refusal’ and ‘response’ arguments. Arguments were guided by common concepts such as the value of herd immunity, the prospect of harm to the child or others in the community and legal perspectives and precedents. The normative significance of parental trust, distrust, and uncertainty was a consideration unique to the ‘refusal’ arguments literature, driven in part by the five parental accounts from the special issue of Narrative Inquiry in Bioethics included in our sample. The concepts of inequity, and the duties of governments and practitioners only appeared in ‘response’ arguments. This is unsurprising: it reflects the purpose and perspective of these writers. An analysis of policy options is often required to bring inequity into view, and both clinicians and policymakers have obligations by virtue of their roles that can inform thinking about the right thing to do.

Many of the arguments justifying vaccine refusal aligned with the wider literature on the perspectives of non-vaccinating parents who value the freedom to make health decisions as caregivers, in what they perceive to be the best interest of their children [ 20 , 21 ]. These decisions are often based on doubts about vaccine safety or efficacy and are commonly initiated by a negative experience [ 19 , 20 , 22 ]. Unsurprisingly, arguments against rejecting childhood vaccines reflected the broader literature on how vaccine-supporting people view non-vaccination— including views that non-vaccinators are misinformed and disrupt social order, and that their actions are not based on reason or shared social values [ 23 ]. Common negative descriptors such as “anti-vaxxer” have similar valence in social discourse [ 24 ]. Those writing about vaccination should be aware of the potential for stigmatization and “othering” that can result by framing non-vaccination as a failure of parents [ 25 ]. When such arguments are used to inform policy and practice responses to non-vaccination, it introduces the potential for negative psychosocial impacts and further alienation of non-vaccinating parents.

Most ‘response’ arguments dealt with the justifiability of mandates and coercive policy. Generally, authors in favour of mandates prioritised the good of society; those against mandates prioritised individual choice. The large number of papers we found on mandates is unsurprising, given that these policies have been contentious. In Australia, federal and most state governments have mandates that require children to be vaccinated to be enrolled in childcare and for their families to be eligible for government financial assistance [ 26 ] Key political, academic and industry stakeholders argue that these mandates are designed to increase vaccination rates for the benefit of society [ 27 ]. On the other hand, Australian non-vaccinating parents express a belief that their children do not pose a threat to society, that all children should be treated in the same way, and that all parents should be able to make decisions for their children, regardless of vaccination status [ 28 ]. These perceptions of policy makers and non-vaccinating parents broadly represent the opposing arguments about mandates presented in this review. Facilitating a middle-ground approach to policy implementation may require closer attention to the values underlying these opposing views, and using a procedurally just approach to weigh them against one another.

In the context of an increasing number of systematic reviews in the field of bioethics, there has been recent criticism emerging about the use of these methods in bioethics. For example, Birchley and Ives (2022) argue that such methods are designed and therefore better suited to aggregation of quantitative data and not the complex and subjective nature of bioethical concepts and the theory-generating and interpretive approaches they require [ 29 ]. We argue that our application of the framework systematic review method - one of many well-established methods for systematic review and synthesis of qualitative and conceptual data - is appropriate for this research question and the application of our findings. Vaccine policy and practice requires a synthesis of what is known on relevant issues, and a systematic approach such as that used here provides a useful summary of the breadth of relevant ethical issues in a format that is accessible to policymakers. Our review has some limitations. Our aim was to map the range of normative arguments about vaccination refusal and policy. We did not have scope to present a novel ethical argument in response to our findings; this is an aim for future empirical and theoretical research. Most of the included literature focuses on high-income settings, predominantly the United States and the United Kingdom. In low-income settings, health services are often harder to access and levels of and reasons for vaccine rejection also differ in these settings. For example, political and cultural factors have been implicated in polio vaccine rejection in Nigeria [ 30 ], while low literacy, unemployment, and owning a mobile phone have been associated with polio vaccine refusal in Pakistan [ 31 ]. Our sampling period included a special issue of Narrative Enquiry in Bioethics which published narratives written by parents to communicate their normative positions on vaccination. These were mostly written by non-vaccinating parents and made up over one third of all arguments in the literature that support refusal. This is a strength in that it expanded the range of views represented in the review. However, it is also a limitation in that if this special issue had not been published within our sampling period, the range of arguments would have been more strongly skewed against vaccine refusal. These papers artificially increased the proportion of arguments in the scholarly domain that argue for vaccine refusal. It is a strength of our methodology that we were able to identify the unique perspective from which they were written and position them separately in our literature synthesis so that our representation of the literature distribution is not artificially skewed.

This review highlights an opportunity for interdisciplinary collaboration to widen the scope and reach of normative arguments about non-vaccination. Such collaboration can facilitate a broader understanding of and engagement with the ethical issues that may be relevant for practitioners, policymakers, and researchers in deciding how to respond to non-vaccinating parents. Arguments about the justifiability of non-vaccination and what should be done about it have the potential to positively influence routine childhood vaccination rates but can also alienate non-vaccinating families if not deployed with their perspectives in mind. There is an avenue for future work to further understand the influence of cultural context on normative arguments, especially within low- and middle-income settings. Moreover, there is an opportunity to further explore the influence and translation of scholarly ethical arguments into policy and practice responses to childhood non-vaccination.

Data Availability

The datasets generated and/or analysed during the current review are not publicly available, however the search terms used to generate the dataset are included in this published article.

Spier RE. Perception of risk of vaccine adverse events: a historical perspective. Vaccine. 2001;20:78–S84. https://doi.org/10.1016/S0264-410X(01)00306-1

Article   Google Scholar  

Nandi A, Shet A. Why vaccines matter: understanding the broader health, economic, and child development benefits of routine vaccination. Hum Vaccines Immunotherapeutics. 2020;16(8):1900–04. https://doi.org/10.1080/21645515.2019.1708669

Siddiqui M, Salmon DA, Omer SB. Epidemiology of vaccine hesitancy in the United States. Hum Vaccines Immunotherapeutics. 2013;9(12):2643–48. https://doi.org/10.4161/hv.27243

Beard FH, Hull BP, Leask J, et al. Trends and patterns in vaccination objection, Australia, 2002–2013. Med J Aust. 2016;204(7):275–75.

Ward PR, Attwell K, Meyer SB, et al. Understanding the perceived logic of care by vaccine-hesitant and vaccine-refusing parents: a qualitative study in Australia. PLoS ONE. 2017;12(10):e0185955.

Ward PR, Attwell K, Meyer SB, et al. Risk, responsibility and negative responses: a qualitative study of parental trust in childhood vaccinations. J Risk Res. 2017;1–14. https://doi.org/10.1080/13669877.2017.1391318

Wiley KE, Leask J, Attwell K, et al. Parenting and the vaccine refusal process: a new explanation of the relationship between lifestyle and vaccination trajectories. Soc Sci Med. 2020;263:113259.

Yaqub O, Castle-Clarke S, Sevdalis N, et al. Attitudes to vaccination: a critical review. Soc Sci Med. 2014;112:1–11.

Brewer NT, Chapman GB, Rothman AJ, et al. Increasing vaccination: putting psychological science into action. Psychol Sci Public Interest. 2017;18(3):149–207.

Attwell K, Navin MC, Lopalco PL, et al. Recent vaccine mandates in the United States, Europe and Australia: a comparative study. Vaccine. 2018;36(48):7377–84.

Attwell K, Seth R, Beard F et al. Financial interventions to increase vaccine coverage. Pediatrics 2020;146(6).

Attwell K, Navin M. How policymakers employ ethical frames to design and introduce new policies: the case of childhood vaccine mandates in Australia. Policy & Politics. 2022;50(4):526–47. https://doi.org/10.1332/030557321x16476002878591

Mertz M, Strech D, Kahrass H. What methods do reviews of normative ethics literature use for search, selection, analysis, and synthesis? In-depth results from a systematic review of reviews. Syst Rev. 2017;6(1):261. https://doi.org/10.1186/s13643-017-0661-x . [published Online First: 20171219].

Australian Bureau of Statistics., 2008, Australian and New Zealand Standard Research Classification (ANZSRC), availabe at: https://www.abs.gov.au/ausstats/[email protected]/0/4ae1b46ae2048a28ca25741800044242?opendocument

Kahrass H, Borry P, Gastmans C et al. PRISMA-Ethics – Reporting Guideline for Systematic Reviews on Ethics Literature: development, explanations and examples 2021 [Available from: OSF Preprints at https://osf.io/g5kfb

McDougall RJ, Notini L. Overriding parents’ medical decisions for their children: a systematic review of normative literature. J Med Ethics. 2014;40(7):448–52. https://doi.org/10.1136/medethics-2013-101446

Brunton G, Oliver S, Thomas J. Innovations in framework synthesis as a systematic review method. Res Synthesis Methods. 2020;11(3):316–30. https://doi.org/10.1002/jrsm.1399

Berry NJ, Henry A, Danchin M, et al. When parents won’t vaccinate their children: a qualitative investigation of Australian primary care providers’ experiences. BMC Pediatr. 2017;17(1):19. https://doi.org/10.1186/s12887-017-0783-2

Helps C, Leask J, Barclay L, et al. Understanding non-vaccinating parents’ views to inform and improve clinical encounters: a qualitative study in an Australian community. BMJ Open. 2019;9(5):e026299. https://doi.org/10.1136/bmjopen-2018-026299

Wiley KE, Leask J, Attwell K, et al. Parenting and the vaccine refusal process: a new explanation of the relationship between lifestyle and vaccination trajectories. Soc Sci Med. 2020;263:113259. https://doi.org/10.1016/j.socscimed.2020.113259

Attwell K, Leask J, Meyer SB, et al. Vaccine rejecting parents’ Engagement with Expert systems that inform Vaccination Programs. J Bioeth Inq. 2017;14(1):65–76. https://doi.org/10.1007/s11673-016-9756-7 . [published Online First: 20161201].

Christou-Ergos M, Leask J, Wiley KE. How the experience of medical trauma shapes Australian non-vaccinating parents’ vaccine refusal for their children: a qualitative exploration. SSM - Qualitative Research in Health. 2022;2:100143. https://doi.org/10.1016/j.ssmqr.2022.100143

Rozbroj T, Lyons A, Lucke J. The mad leading the blind: perceptions of the vaccine-refusal movement among australians who support vaccination. Vaccine. 2019;37(40):5986–93. https://doi.org/10.1016/j.vaccine.2019.08.023 . [published Online First: 20190823].

Court J, Carter SM, Attwell K, et al. Labels matter: use and non-use of ‘anti-vax’ framing in Australian media discourse 2008–2018. Soc Sci Med. 2021;291:114502. https://doi.org/10.1016/j.socscimed.2021.114502

Wiley KE, Leask J, Attwell K, et al. Stigmatized for standing up for my child: a qualitative study of non-vaccinating parents in Australia. SSM Popul Health. 2021;16:100926. https://doi.org/10.1016/j.ssmph.2021.100926 . [published Online First: 20210916].

Attwell K, Drislane S. Australia’s ‘No jab no play’ policies: history, design and rationales. Aust N Z J Public Health. 2022;46(5):640–46. https://doi.org/10.1111/1753-6405.13289

Attwell K, Navin M. How policymakers employ ethical frames to design and introduce new policies: the case of childhood vaccine mandates in Australia. Policy and Politics. 2022;1–22. https://doi.org/10.1332/030557321X16476002878591

Wiley K, Robinson P, Degeling C, et al. Get your own house in order’: qualitative dialogue groups with nonvaccinating parents on how Measles outbreaks in their community should be managed. Health Expect. 2022;25(4):1678–90. https://doi.org/10.1111/hex.13511

Birchley G, Ives J. Fallacious, misleading and unhelpful: the case for removing ‘systematic review’ from bioethics nomenclature. Bioethics. 2022;36(6):635–47. https://doi.org/10.1111/bioe.13024

Yahya M. Polio vaccines—no thank you! Barriers to polio eradication in Northern Nigeria. Afr Affairs. 2007;106(423):185–204. https://doi.org/10.1093/afraf/adm016

Khattak FA, Rehman K, Shahzad M, et al. Prevalence of parental refusal rate and its associated factors in routine immunization by using WHO Vaccine Hesitancy tool: a Cross sectional study at district Bannu, KP, Pakistan. Int J Infect Dis. 2021;104:117–24. https://doi.org/10.1016/j.ijid.2020.12.029

Download references

This review was funded by the Australian National Health and Medical Research Council, grant number GNT1126543.

Author information

Authors and affiliations.

Sydney School of Public Health, The University of Sydney, Edward Ford Building A27, Sydney, 2006, Australia

Kerrie Wiley, Maria Christou-Ergos, Penelope Robinson & Catherine Helps

Australian Centre for Health Engagement, Evidence and Values, The University of Wollongong, Wollongong, 2522, Australia

Chris Degeling & Stacy M Carter

Melbourne School of Population and Global Health, The University of Melbourne, Melbourne, 3010, Australia

Rosalind McDougall

School of Social Sciences, Asian Studies & Politics, International Relations, University of Western Australia, Perth, 6009, Australia

Katie Attwell & Shevaun Drislane

You can also search for this author in PubMed   Google Scholar

Contributions

KW contributed to study design and search strategy development, ran the searches, managed the screening and inclusion process, screened articles for inclusion, extracted data, analysed and interpreted data and co-led manuscript drafting; MC ran updated searches, screened articles for inclusion and extracted data, assisted with analysis and interpretation and co-led manuscript drafting; CD contributed to study design and search strategy development, provided technical guidance, screened articles for inclusion and contributed to manuscript drafts; RM contributed to study design and search strategy development, provided technical guidance, screened articles for inclusion and contributed to manuscript drafts; PR screened articles for inclusion, extracted data, assisted with analysis and contributed to manuscript drafts; KA contributed to search strategy development, screened articles for inclusion and contributed to manuscript drafts; CH screened articles for inclusion and contributed to manuscript drafts; SD screened articles for inclusion and contributed to manuscript drafts; SMC contributed to study design and search strategy development, provided technical guidance, screened articles for inclusion and contributed to manuscript drafts.

Corresponding author

Correspondence to Kerrie Wiley .

Ethics declarations

Ethics approval and consent to participate.

Not applicable.

Consent for publication

Competing interests.

The authors declare no competing interests.

Additional information

Publisher’s note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ . The Creative Commons Public Domain Dedication waiver ( http://creativecommons.org/publicdomain/zero/1.0/ ) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and Permissions

About this article

Cite this article.

Wiley, K., Christou-Ergos, M., Degeling, C. et al. Childhood vaccine refusal and what to do about it: a systematic review of the ethical literature. BMC Med Ethics 24 , 96 (2023). https://doi.org/10.1186/s12910-023-00978-x

Download citation

Received : 20 February 2023

Accepted : 31 October 2023

Published : 08 November 2023

DOI : https://doi.org/10.1186/s12910-023-00978-x

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Vaccination
• Immunization
• Vaccine refusal
• Systematic review
• Normative literature
• Medical ethics

BMC Medical Ethics

ISSN: 1472-6939

• Submission enquiries: [email protected]
• General enquiries: [email protected]

This paper is in the following e-collection/theme issue:

Published on 16.11.2023 in Vol 25 (2023)

A SWOT (Strengths, Weaknesses, Opportunities, and Threats) Analysis of ChatGPT in the Medical Literature: Concise Review

Authors of this article:

• Daniel Gödde 1 , MD, Dr med   ; 
• Sophia Nöhl 2 , BSc   ; 
• Carina Wolf 2   ; 
• Yannick Rupert 2   ; 
• Lukas Rimkus 2   ; 
• Jan Ehlers 3 , Prof Dr   ; 
• Frank Breuckmann 4, 5 , MD, Prof Dr   ; 
• Timur Sellmann 6, 7 , MD, Dr med, MHBA  

1 Department of Pathology and Molecularpathology, Helios University Hospital Wuppertal, Witten/Herdecke University, Witten, Germany

2 Faculty of Health, Witten/Herdecke University, Witten, Germany

3 Department of Didactics and Education Research in the Health Sector, Faculty of Health, Witten/Herdecke University, Witten, Germany

4 Department of Cardiology and Vascular Medicine, West German Heart and Vascular Center Essen, University Duisburg-Essen, Essen, Germany

5 Department of Cardiology, Pneumology, Neurology and Intensive Care Medicine, Klinik Kitzinger Land, Kitzingen, Germany

6 Department of Anaesthesiology I, Witten/Herdecke University, Witten, Germany

7 Department of Anaesthesiology and Intensive Care Medicine, Evangelisches Krankenhaus BETHESDA zu Duisburg, Duisburg, Germany

Corresponding Author:

Daniel Gödde, MD, Dr med

Department of Pathology and Molecularpathology

Helios University Hospital Wuppertal

Witten/Herdecke University

Alfred-Herrhausen-Straße 50

Witten, 58455

Phone: 49 202 896 2541

Fax:49 202 896 2739

Email: [email protected]

Background: ChatGPT is a 175-billion-parameter natural language processing model that is already involved in scientific content and publications. Its influence ranges from providing quick access to information on medical topics, assisting in generating medical and scientific articles and papers, performing medical data analyses, and even interpreting complex data sets.

Objective: The future role of ChatGPT remains uncertain and a matter of debate already shortly after its release. This review aimed to analyze the role of ChatGPT in the medical literature during the first 3 months after its release.

Methods: We performed a concise review of literature published in PubMed from December 1, 2022, to March 31, 2023. To find all publications related to ChatGPT or considering ChatGPT, the search term was kept simple (“ChatGPT” in AllFields). All publications available as full text in German or English were included. All accessible publications were evaluated according to specifications by the author team (eg, impact factor, publication modus, article type, publication speed, and type of ChatGPT integration or content). The conclusions of the articles were used for later SWOT (strengths, weaknesses, opportunities, and threats) analysis. All data were analyzed on a descriptive basis.

Results: Of 178 studies in total, 160 met the inclusion criteria and were evaluated. The average impact factor was 4.423 (range 0-96.216), and the average publication speed was 16 (range 0-83) days. Among the articles, there were 77 editorials (48,1%), 43 essays (26.9%), 21 studies (13.1%), 6 reviews (3.8%), 6 case reports (3.8%), 6 news (3.8%), and 1 meta-analysis (0.6%). Of those, 54.4% (n=87) were published as open access, with 5% (n=8) provided on preprint servers. Over 400 quotes with information on strengths, weaknesses, opportunities, and threats were detected. By far, most (n=142, 34.8%) were related to weaknesses. ChatGPT excels in its ability to express ideas clearly and formulate general contexts comprehensibly. It performs so well that even experts in the field have difficulty identifying abstracts generated by ChatGPT. However, the time-limited scope and the need for corrections by experts were mentioned as weaknesses and threats of ChatGPT. Opportunities include assistance in formulating medical issues for nonnative English speakers, as well as the possibility of timely participation in the development of such artificial intelligence tools since it is in its early stages and can therefore still be influenced.

Conclusions: Artificial intelligence tools such as ChatGPT are already part of the medical publishing landscape. Despite their apparent opportunities, policies and guidelines must be implemented to ensure benefits in education, clinical practice, and research and protect against threats such as scientific misconduct, plagiarism, and inaccuracy.

Introduction

ChatGPT is a 175-billion-parameter natural language processing model that can generate conversation-style responses to user input. Parameters are the numerical values that determine how a neural network processes input data and produces output data. They are learned from data during the training process, and they encode the knowledge and skills of the model [ 1 , 2 ]. Since its launch by OpenAI, ChatGPT has stimulated widespread conversation and momentum across various human sciences, including medicine, as demonstrated by over 1250 publications related to ChatGPT indexed in PubMed in 2023 so far. General interest is reflected by the rapid increase in user numbers within a very short time—after just 1 week, ChatGPT had reached the 1 million-user mark, and by January 2023, the number of users had exceeded 100 million [ 1 , 3 ]. It enables humans to interact and discuss with an artificial intelligence (AI) chatbot on a broad range of topics. Since it became known that ChatGPT was able to pass the United States Medical Licensing Examination, performing at a level comparable to a third-year medical student [ 4 ], it has garnered even more interest. Preliminary evidence shows that ChatGPT has promising applications across the clinical workflow, especially regarding clinical decision-making, narrowing the final diagnosis, and clinical management [ 5 ]. Moreover, ChatGPT and similar generative AI tools have specific applications within medical education, including clinical vignette generation and communication training with AI virtual patients [ 5 - 7 ]; however, it poses several challenges that universities need to carefully address [ 8 ]. Tested on the verbal scale of the Wechsler Adult Intelligence Scale (WAIS), an intelligence quotient of 155 was demonstrated for ChatGPT [ 9 ]. When the authors asked ChatGPT to explain its role in medical literature,” it responded as follows:

As an AI language model, ChatGPT’s role in medical literature is to provide information and insights related to health care and medicine based on its knowledge of the subject matter. ChatGPT can help researchers and health care professionals by providing quick access to information on a wide range of medical topics, including symptoms, diagnoses, treatments, and outcomes. ChatGPT can also assist in generating summaries and abstracts of medical articles and papers, making it easier for health care professionals to keep up with the latest developments in their field. Additionally, ChatGPT can assist in developing natural language processing applications that can improve the efficiency and accuracy of medical data analysis and interpretation. However, it’s important to note that ChatGPT is not a substitute for medical professionals and should not be used to make medical decisions. It is always recommended to consult with a licensed health care provider for medical advice and treatment. [ChatGPT response]

Although these features are promising, the technology is still vulnerable to misuse and abuse due to the lack of regulation. It can be tempting to save time by creating manuscripts using ChatGPT. However, there is a risk that false information will be published or used, which may compromise patient safety. Since its release, over 200 papers have addressed issues using the search term “ChatGPT.” This review aimed to analyze the role of ChatGPT in the medical literature during the first 3 months after its release. The main focus is on how ChatGPT can help authors with research, data analysis, and even writing medical papers, although articles, publishing journals, and authors were studied in more detail. To provide an overview, uncover more information about its potential, and create hypotheses for further research, we undertook this concise review on the role of ChatGPT including a SWOT (strengths, weaknesses, opportunities, and threats) analysis to define its potential, especially for medical publishing.

Study Design: Search Strategy and Selection Criteria

To extract all publications related to or considering ChatGPT from December 1, 2022, to March 31, 2023, we searched PubMed for the Medical Subject Headings (MeSH) term “ChatGPT” in AllFields on April 1, 2023. All full-text publications in German or English published during this period were included. In the next step, we excluded articles that were not written about the use of ChatGPT but where ChatGPT acted as coauthor or where ChatGPT was used to support the text generation ( Textbox 1 ). The final reference list was generated based on relevance to the broad scope of this review.

Inclusion criteria

• Fully retrievable articles
• Published in English and German
• Published between December 1, 2022, and March 31, 2023
• Human author(s)

Exclusion criteria

• Nonretrievable articles
• Published in languages other than English or German
• Published before December 1, 2022, and after March 31, 2023
• Authored by ChatGPT

Data Analysis

All accessible publications were evaluated according to the following specifications by the authors: title, publication date, PubMed ID, author (including publication experience, specialization), journal title (including specialization), impact factor, publication modus, article type, study type, publication speed, type of ChatGPT integration, content analysis (evidence for strengths, weaknesses, opportunities, and/or threats), and further comments. For evaluation, the full texts were divided between the authors. Each publication was first evaluated and categorized by an author concerning the given criteria. The results were documented in a collaborative table. To increase reliability and validity, the results were then reviewed by a second author. In case of differences in the evaluation, a discussion between the 2 authors took place until a consensus was reached. If it could not be reached, the evaluation was performed by a third author, and a majority decision was made.

Publications were primarily classified according to the specifications of PubMed. For better comprehensibility, a “studies” category was created, defined as “a method of research in which a problem is identified, relevant data are gathered, a hypothesis is formulated, and the hypothesis is empirically tested.” This category allowed for differentiation from nonempirical publications such as editorials. All identified articles were scanned for qualitative (ie, a collection of text-based data, such as interviews and focus groups, usually hypothesis-generating) versus quantitative (ie, a collection of number-based data, such as measurements, questionnaires with associated statistics, usually hypothesis-testing) content. We also chose to discriminate between mixed methods research (ie, a combination of qualitative and quantitative content) and reviews and meta-analysis. Article contents were analyzed in reporting on the use or actual, partial, or full use of ChatGPT in the drafting of the article. In this context, attention was also paid to the correlation between the share of ChatGPT in the preparation of the manuscript (not at all, partially, completely) and the achievable impact factor. The conclusions of the articles were entered in the table in the short form to allow for later SWOT analysis. The publishing speed and the presence of preprint were documented. To better compare the course of the number of actual published papers on ChatGPT, an article count was displayed by week and compared to weekly article releases during the COVID-19 outbreak, an impactful event in current medical history.

Journals publishing articles on ChatGPT were evaluated regarding title, discipline of natural science, actual impact factor, and open access versus traditional publishing. The publishing speed (including preprint servers) was only included in the analysis if given in the paper itself or alongside the date of submission and publication.

To obtain further information about the authors publishing on the topic, the number of first and last authorships of each first author in PubMed was determined for the years between 2020 and 2022. In addition, the specialty of each first author was also determined via the affiliations in the paper, PubMed, or via the ORCID (Open Researcher and Contributor ID).

SWOT Analysis

The authors broke into groups of two to work on the first part of the SWOT analysis. They examined all the documented comments to determine if they fit into their area. A consensus had to be reached between the authors. If this was not possible, it was noted. Then, the domains were swapped (strengths versus threats and weaknesses versus opportunities), and the previous divisions were reviewed. Particular attention was paid to comments that did not previously reach consensus. Each comment was thus assigned by 4 authors. If consensus decisions could not be reached, the majority decision counted.

Statistical Analysis

The primary endpoint was strengths, weaknesses, opportunities, and threats of ChatGPT use in medical literature, with subcategories of author, article, and journal type. All data were analyzed on a descriptive basis. Data were presented as means and SD unless otherwise stated. Statistical analysis was performed descriptively using Microsoft Excel for Office 365 (Microsoft Corp) and PSPP (GNU Project, Free Software Foundation). The Student t test, Levene test, and Mann-Whitney U test were applied as appropriate. P <.05 was considered to represent statistical significance.

From December 1, 2022, to March 31, 2023, a total of 178 papers using the search term “ChatGPT” were published in PubMed; among them, 6 (3.4%) were published in December 2022, 16 (9%) in January 2023, 68 (38.2%) in February 2023, and 88 (49.4%) in March 2023. After a thorough human review, 18 papers had to be excluded, 11 because they were written with but not about ChatGPT, 4 that were not retrievable as full text, and 2 that were neither written in English nor German. One paper was just an erratum note. Figure 1 shows the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) flowchart of ChatGPT-related publications (modified after [ 10 ]).

The majority of the articles were brief statements like editorials, or letters to the editor (n=77, 48.1%). Essays or commentaries (n=43, 26.9%) represented the second largest portion of the articles. Research studies not further specifiable (n=21, 13.3%), reviews, news, case reports (each n=6, 3.8%), and meta-analyses (n=1, 0.6%) were less frequent. No randomized controlled trial (RCT) could be identified. Table 1 shows the distribution of article types according to the specifications of PubMed publication type. Of all the articles, 80% (n=128) contained nonempirical data and 20% (n=32) contained empirical data. Among these, 6.9% (n=11) were qualitative, 8.8% (n=14) were quantitative, and 1.9% (n=3) were mixed methods. Regarding the proportion of ChatGPT within the article, 11.9% (n=19) of all articles were written at least partially with ChatGPT. The average impact factors are displayed in Table 2 .

a The name of the publication was adopted analogously to the terminology in PubMed. “News” in this context means information or reports about recent events, whereas “study” means an organized experiment.

a Indicates nonsignificant P values. The Levene test (P =.001) indicated that the t test, although primarily significant ( P =.003), was not robust, so statistical significance was also calculated using the Mann-Whitney U test ( P =.4).

To illustrate scientific interest in the topic, as measured by the number of publications, Figure 2 shows the comparison to the number of COVID-19–related publications during the first 12 weeks of 2020 [ 11 ].

The papers were published in journals covering a wide range of scientific disciplines. Table 3 shows an overview of the specialty distribution of journals published on ChatGPT. The current impact factor of the represented journals ranged from 0 to 96.216, with a median of 5.144 (IQR 3.352-11.325). Overall, 45.6% (n=73) of all articles were published “traditionally” in contrast to 54.4% (n=87) that were published as open access. Of those, 5% (n=8) of “open access” publications were provided on preprint servers in advance. Data on publication speed were accessible in 33.1% (n=53) of all evaluated articles. The average time to publication was 16 days, ranging from 4 to 83 days.

The authors of the reviewed papers had a median of 5 (IQR 1-12; range 0-94) first and a median of 1 (IQR 0-6; range 0-61) last authorships in the years spanning 2020 to 2022. Their area of expertise spanned all medical specialties, including science journalism, bioinformatics, nursing, humanities, economics, and law. Table 4 gives an overview of the specialty distribution of the first authors.

We were able to detect 408 quotes (in the 160 papers included) that provided information on strengths, weaknesses, opportunities, and threats. Of those, most were related to weaknesses (n=142, 34.8 %) and least to opportunities (n=68, 16.7%). Quotes on strengths (n=117, 28.7%) and threats (n=81, 19.9%) were mentioned less frequently. Among the most prevalently cited weaknesses were limited abilities [ 12 , 13 ], lack of accuracy/correctness [ 14 , 15 ], citation problems [ 16 , 17 ], and the need for verification [ 18 , 19 ]. Limited abilities in the context of ChatGPT meant not being able to provide reliable facts and sources [ 12 ], limitations in understanding complex scientific concepts, or a limited scope of expertise and a lack of accountability [ 13 ]. In addition, limited abilities included, for example, the inability to think like a human and evaluate interpersonal aspects, as well as recognize emotions and act on them. Strengths, on the other hand, included reduced workload [ 14 , 20 - 22 ], data summarization [ 23 ], and results rated as positive and high-quality by the authors themselves [ 15 , 24 - 28 ]. Among the threats captured most frequently were plagiarism (meaning not providing sources), hallucination (meaning making up sources), scientific misconduct, and ethical concerns [ 25 , 29 - 31 ], whereas major opportunities were seen in supporting different faculties [ 24 , 32 , 33 ]. For example, Goodman et al [ 32 ] mentioned that ChatGPT could improve patient education by personalizing and targeting information to the patient’s education level. Due to the variability in the mentions, we decided to carry out a semiqualitative SWOT analysis. Figure 3 shows the results, conclusions, and suggestions. Raw data on all the aforementioned information can be found in Multimedia Appendix 1 .

Principal Results

To our knowledge, this is the first review of ChatGPT including a SWOT analysis to date, summarizing all articles published in PubMed since ChatGPT launched in November 2022 through the end of March 2023. In addition to a whole series of metric results, the experiences of authors writing about ChatGPT were also critically reviewed in the context of the SWOT analysis. The density and quality of data available at the time of data collection did not allow the use of further, more specific methods and tools to assess the risk of bias. To the best of our knowledge, no similarly comprehensive study on the topic exists to date.

Concerning the article types, it was interesting to see that so far, only 1 RCT has been published about ChatGPT [ 34 ]. RCTs on ChatGPT are potentially ambitious and partially difficult to accomplish, but their data are needed to gain more evidence. In this review, the majority of the articles were of a shorter nature (ie, editorials, letters, features, essays, or commentaries).

Journals from the ranks of clinical medicine have published the most articles on ChatGPT, followed by education and others. This resembles the results from authorship. Both aspects (ie, authorship and journal) show the wide application potential for ChatGPT across many specialist areas, as would be expected from a large language model (LLM). When considering the impact factor of the journals, it is interesting to note that some articles were published in journals with no impact factor, although even highly reputable fundamental research journals, such as Science or Nature, and clinical journals, such as the British Medical Journal (BMJ) or the Lancet, have covered the topic. This proves the importance and relevance of ChatGPT in science, education, and clinical work. Out of the 160 papers that were evaluated, 138 (86.3%) were published in journals with an impact factor. Whether a paper was or was not at least partially written with ChatGPT did not have a significant influence on the journal’s impact factor.

Despite the extensive application possibilities of ChatGPT in both medical and nonmedical fields, the publication frequency has not kept pace with the surge seen in COVID-19–related research. This is somewhat surprising considering the significant media attention ChatGPT has received due to remarkable achievements such as passing medical licensing exams, assisting in radiologic decision-making interpretation, and even generating patient clinic letters [ 4 , 25 , 26 ].

Because ChatGPT is also an event of global significance, we deliberately chose the pandemic as a point of comparison. However, the global health crisis likely served as a stronger catalyst to address the issue, although no relevant difference was seen during the first 4 weeks after the onset of the pandemic compared to the appearance of ChatGPT. Interestingly, it is worth noting that publication speed, if quantifiable, averaged 16 days (ranging from 4 to 83), which is significantly faster than what has been reported in other studies published in biomedical journals [ 35 - 37 ]. However, it is important to recognize that the majority of papers in our review were editorials or commentaries. The quicker publication speed is not as surprising in this context, as these types of publications are easier to produce than larger studies. Furthermore, it is important to note that this statement needs some qualification since corresponding data were only available for about one-third of the publications. This necessitates a more nuanced and less definitive discussion. Alongside the spectrum of journals containing ChatGPT publications, the proportion of preprint and open-access articles should also be considered as influential factors. A multivariate analysis showed that web-based publishing is strongly associated with reduced submission-to-publication time [ 37 ]. It must be emphasized that data on submission speed were only available in about one-third of all articles, which is a limiting factor. However, in combination with the higher proportion of quantitative and nonempirical data, we assume that open access and preprints contributed to the fast publication times.

It is difficult to create a comprehensive author profile in this area due to distribution patterns and publication frequencies. However, most authors seem to come from the “clinical medicine” field, which entails working directly with patients. Surprisingly, education, despite being frequently mentioned and an obvious ChatGPT application area, had a lower representation.

Notably, many authors were not newcomers to publishing. Increased public interest in ChatGPT’s medical application seemed to have given them an incentive to conduct research and publish quicker than before. The worth of engaging with ChatGPT is evident from the average impact factor that could be achieved with a publication on this topic, and whether or not an article was written with the help of ChatGPT did not seem to affect the outcome. The median impact of 5.144 (regardless of ChatGPT usage) falls within a range where only 7.9% (n=979) of other journals in a comparison of 13,000 selected scientific journals across 27 major prominent research categories were situated [ 38 ].

In addition, despite the allure of using AI in manuscript creation, only slightly under 12% (18/160) of authors used AI, or at least indicated they had. However, since there are no official guidelines for declaring ChatGPT usage in new research, it could be possible that some authors did not disclose its usage. Acknowledging AI use for writing assistance was among the most frequently cited SWOT (which will be discussed later in this section). Thus far, however, ChatGPT usage is not clearly superior or inferior in terms of the impact achieved.

Interestingly, in our SWOT analysis, ChatGPT weaknesses were identified more prominently than strengths, which came in second. It must be said, however, that for the sake of comparability, we weighed the strengths, weaknesses, opportunities, and threats listed by authors equally, regardless of the type of article they were listed in. This is important because essays and opinion pieces were the prevailing types of articles in our analysis, outweighing a more nuanced representation of advantages and disadvantages based on actual trials and scientific research. Given the sheer number of articles that we analyzed, this approach allowed us to make fair comparisons at the time.

When examining the frequency of the SWOT citations, it appeared that many authors provided descriptive accounts of weaknesses and strengths but offered fewer perspectives or ideas for further handling or development of ChatGPT developed from their findings. This is reinforced by the fact that threats were only cited in 19.9% (n=81) papers, and opportunities were mentioned in 16.7% (n=68) compared to weaknesses (n=142, 34.8%).

The SWOT analysis, originally defined as a “strategic planning and strategic management technique used to help a person or organization identify strengths, weaknesses, opportunities, and threats related to business competition or project planning” [ 39 ], is used to identify the favorable and unfavorable internal and external factors that impact the objectives of a venture. It is valued for its usability and status as a “tried-and-true tool” for strategic analysis. However, points of criticism include limitations such as potential bias, inconsistency in analysis compliance, and the dominance of certain team members [ 40 - 43 ]. To address some of these shortcomings, we used a modified Delphi process to analyze the quotes. Furthermore, we designed our SWOT analysis as a starting point for discussion, considering it a suitable tool for analyzing ChatGPT in its early stages and generating some ideas for moving forward, particularly in a rapidly changing environment.

Thus far, ChatGPT has been used to write essays, pass exams, translate knowledge for various peer groups, and generate comments on a wide array of topics. However, it has become clear during its application that ChatGPT is, at least until 2021, “apparently “knowledge limited.” This limitation means that it often generates information and facts that are fictional, detectable only by experts with the relevant expertise.

The existing publications on the topic serve a dual purpose. On the one hand, they contribute to the ongoing improvement of AI, making it safer for use in various contexts. On the other hand, they have identified fields where ChatGPT can presumably be applied safely. These applications include summarizing large data sets and producing easily understandable text.

Nonetheless, caution must be exercised when using ChatGPT, as in several cases, sources have been freely invented (hallucination) [ 14 , 25 ] or copied (plagiarism) [ 16 , 29 , 30 , 44 ]; therefore, the accurateness of content created by ChatGPT must always be questioned.

Areas unsuitable for ChatGPT’s application include writing scientific papers with references, composing resumes, or writing speeches. In these domains, it has already been shown that ChatGPT can create partially or completely fictitious passages [ 16 , 29 , 30 , 44 ], which cannot withstand critical review.

After our concise review, it is clear that ChatGPT serves more as an exploratory tool than a reliable tool for scientific work. This is not inherently negative; playful interactions with ChatGPT can identify strengths and areas for improvement, which developers and programmers can then address. In any case, it is crucial to avoid monopolization (eg, through the displacement of competitors), as it could lead to issues like a lack of transparency in data sources [ 45 ] or global commercialization with ethical-economic imbalances [ 29 ]. So far, over 30 alternatives for ChatGPT exist, including OpenAI Playground, Jasper Chat, Bard, and Bing AI [ 46 ]. Ideally, such large-scale software would be open source.

Another area of major concern is the ability to detect AI-generated scientific output. Existing AI detection software, such as GPTZero, or related products like GLTR, GPTKit, OpenAI, and Output Detector are based on scanning for perplexity (typically lower in AI) and burstiness (typically higher in AI) [ 47 ]. Perplexity and burstiness are key AI metrics, aiding our understanding of how LLMs write and how humans can detect AI-generated content. Perplexity evaluates LLM performance, while burstiness is linked to the SD of sentence lengths, making it a measure of text efficiency. Their most obvious, clear limitation is that texts are not analyzed for context but only for writing patterns, potentially allowing AI to go undetected.

Initial data from a comparative study of AI output detectors, plagiarism detectors, and blinded human reviewers show promising results. In that study, AI output detectors successfully identified most AI-generated abstracts, with an area under the receiver operating characteristic (AUROC) curve of 0.94 [ 48 ]. However, it is vital to keep pace with the rapid development of new AI interactions like GPT-3 or GPT-4, all while maintaining an alert, skeptical perspective to uphold data integrity.

The AI Phenomenon Worldwide

ChatGPT, specializing in written conversations, has broad applications across countless domains, underlining the absence of any concrete regulation. As of April 2023, ChatGPT is unavailable in China and other countries with heavy internet censorship, including North Korea, Iran, and Russia. While it is not officially blocked, OpenAI does not allow users from these countries to sign up. Interestingly, several large tech companies in China are developing alternatives [ 49 ]. Italy became the first Western country to ban ChatGPT, and various other Western governments, such as Germany, the United Kingdom, and Canada, are currently exploring ways to regulate AI use. The United States has not yet proposed any formal rules to bring oversight to AI technology [ 49 ].

The AI Phenomenon in Medicine

During the review, the threat of being unable to detect the use of ChatGPT in the writing process and the associated lack of reproducibility of its written content were mentioned [ 33 ]. For example, Aubignat and Diab [ 16 ] cited a study that examined the ability of both a plagiarism detector and a group of reviewers to accurately identify abstracts written by ChatGPT across various journals. Unsurprisingly, they struggled to correctly determine whether the content was original or plagiarist, leading to the conclusion that ChatGPT can write “credible scientific abstracts” [ 16 ]. Suggested solutions include consistently mentioning ChatGPT’s possible contribution [ 24 ], albeit not as an author [ 44 , 50 ] but more as an “acknowledgement” [ 51 ].

Recently, the World Association of Medical Editors (WAME) clearly stated that “AI cannot be an author” and emphasized the responsibility and reproducibility of human authors [ 52 ]. A similar stance is also reflected in the criteria of the International Committee of Medical Journal Editors (ICMJE) [ 53 ]. Major publishers have started to integrate these recommendations into their policies [ 54 ]. Other sources have suggested the inclusion of AI output detectors in the editorial process and clear disclosure if these technologies are used [ 48 ].

AI has always fired the human imagination, as can be seen from famous movies like Star Trek, Star Wars , Terminator , and Aliens , always accompanied by a resonating, undefined fear that AI may “overtake” us one day—with potentially deleterious consequences. Despite these easily visualizable and seemingly apocalyptic dangers, one should not dismiss the sheer unlimited and fascinating possibilities offered by AI. Nevertheless, after comparing and evaluating the various strengths, weaknesses, opportunities, and threats posed by ChatGPT, we, the authors, firmly believe that strict and clear regulations on many levels are necessary to fully leverage its potential. In our humble judgment, it seems wise to keep a low profile right now, as ChatGPT itself points out at least some of its weaknesses when asked:

As an artificial intelligence language model, I do not have a role in the discussion about ChatGPT in the medical literature. However, I can provide information and answer questions related to my capabilities and limitations as a language model, as well as share insights on how natural language processing technology is being applied in health care and medical research. [ChatGPT response]

Acknowledgments

The authors would like to thank Dr Christian Burisch (private researcher, Essen, Germany) for his help with the statistics and drafting of the manuscript.

All listed authors declare that all 4 criteria for authorship in the International Committee of Medical Journal Editor (ICMJE) recommendations were met individually. All authors confirm that they had full access to all the data in the study and accept responsibility for submitting the data for publication. All authors claim responsibility and accountability for the originality, accuracy, and integrity of the work. Notably, artificial intelligence (AI) and AI-assisted technologies were used twice as examples and clearly marked as such in the manuscript.

Data Availability

Without exception, all data collected for this study, including individual participant data and a data dictionary defining each field in the set, will be made available to others. This also includes additional, related documents that will be published and made available upon request by email to the corresponding author.

Authors' Contributions

DG, SN, CW, YR, LR, JE, FB, and TS were involved in the concept and design of the above review. All authors made major contributions to literature search, data collection, data analysis, and data interpretation. DG, SN, CW, YR, LR, JE, FB and TS wrote and edited the manuscript. DG and TS created all the figures. All authors read and approved the final manuscript.

Conflicts of Interest

None declared.

PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) checklist and raw data from the review.

• Shevchuk V. GPT-4 parameters explained: everything you need to know. Level Up Coding. URL: https:/​/levelup.​gitconnected.com/​gpt-4-parameters-explained-everything-you-need-to-know-e210c20576ca, [accessed 2023-09-26]
• Meffert K. Künstliche intelligenz glossar – die wichtigsten begriffe. DSGVO Blog. URL: https://dr-dsgvo.de/kuenstliche-intelligenz-glossar-die-wichtigsten-begriffe [accessed 2023-09-26]
• Dennean K, Gantori S, Limas DK, Pu A, Gilligan R. Let's chat about ChatGPT. UBS. URL: https://www.ubs.com/us/en/wealth-management/insights/market-news/article.1585717.html [accessed 2023-09-26]
• Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor RA, et al. How Does ChatGPT perform on the United States Medical Licensing Examination? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ 2023 Feb 08;9:e45312 [ https://mededu.jmir.org/2023//e45312/ ] [ CrossRef ] [ Medline ]
• Rao A, Pang M, Kim J, Kamineni M, Lie W, Prasad AK, et al. Assessing the utility of ChatGPT throughout the entire clinical workflow. medRxiv. Preprint posted online Feb 26, 2023 [ https://doi.org/10.1101/2023.02.21.23285886 ] [ CrossRef ] [ Medline ]
• Benoit J. ChatGPT for clinical vignette generation, revision, and evaluation. medRxiv. Preprint posted online Feb 8, 2023 [ CrossRef ]
• Shorey S, Ang E, Yap J, Ng ED, Lau ST, Chui CK. A virtual counseling application using artificial intelligence for communication skills training in nursing education: development study. J Med Internet Res 2019 Oct 29;21(10):e14658 [ https://www.jmir.org/2019/10/e14658/ ] [ CrossRef ] [ Medline ]
• Sinhaliz S, Burd L, Du PJ. How ChatGPT could revolutionize academia - the AI chatbot could enhance learning, but also creates some challenges. IEEE Spectrum. URL: https://spectrum.ieee.org/how-chatgpt-could-revolutionize-academia [accessed 2023-09-26]
• Roivainen E. I gave ChatGPT an IQ test. Here’s what I discovered. Scientific American. URL: https://www.scientificamerican.com/article/i-gave-chatgpt-an-iq-test-heres-what-i-discovered/, [accessed 2023-01-05]
• Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 2021 Mar 29;372:n71 [ http://www.bmj.com/lookup/pmidlookup?view=long&pmid=33782057 ] [ CrossRef ] [ Medline ]
• Kambhampati SB, Vaishya R, Vaish A. Unprecedented surge in publications related to COVID-19 in the first three months of pandemic: A bibliometric analytic report. J Clin Orthop Trauma 2020 May;11(Suppl 3):S304-S306 [ https://europepmc.org/abstract/MED/32405191 ] [ CrossRef ] [ Medline ]
• Wen J, Wang W. The future of ChatGPT in academic research and publishing: A commentary for clinical and translational medicine. Clin Transl Med 2023 Mar 20;13(3):e1207 [ https://europepmc.org/abstract/MED/36941774 ] [ CrossRef ] [ Medline ]
• Biswas SS. Potential use of ChatGPT in global warming. Ann Biomed Eng 2023 Jun 01;51(6):1126-1127 [ CrossRef ] [ Medline ]
• Shen Y, Heacock L, Elias J, Hentel KD, Reig B, Shih G, et al. ChatGPT and other large language models are double-edged swords. Radiology 2023 Apr 01;307(2):e230163 [ CrossRef ] [ Medline ]
• Zhu J, Jiang J, Yang M, Ren ZJ. ChatGPT and environmental research. Environ Sci Technol 2023 Mar 21 [ CrossRef ] [ Medline ]
• Aubignat M, Diab E. Artificial intelligence and ChatGPT between worst enemy and best friend: The two faces of a revolution and its impact on science and medical schools. Rev Neurol (Paris) 2023 Jun;179(6):520-522 [ CrossRef ] [ Medline ]
• Benichou L, ChatGPT. The role of using ChatGPT AI in writing medical scientific articles. J Stomatol Oral Maxillofac Surg 2023 Oct;124(5):101456 [ CrossRef ] [ Medline ]
• Buvat I, Weber W. Nuclear medicine from a novel perspective: Buvat and Weber talk with OpenAI's ChatGPT. J Nucl Med 2023 Apr 23;64(4):505-507 [ CrossRef ] [ Medline ]
• Johnson D, Goodman R, Patrinely J, Stone C, Zimmerman E, Donald R, et al. Assessing the accuracy and reliability of AI-generated medical responses: an evaluation of the Chat-GPT model. Res Sq 2023 Feb 28;28:A [ https://europepmc.org/abstract/MED/36909565 ] [ CrossRef ] [ Medline ]
• Yeo YH, Samaan JS, Ng WH, Ting P, Trivedi H, Vipani A, et al. Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinoma. Clin Mol Hepatol 2023 Jul 22;29(3):721-732 [ https://europepmc.org/abstract/MED/36946005 ] [ CrossRef ] [ Medline ]
• Rillig MC, Ågerstrand M, Bi M, Gould KA, Sauerland U. Risks and benefits of large language models for the environment. Environ Sci Technol 2023 Mar 07;57(9):3464-3466 [ CrossRef ] [ Medline ]
• Gabrielson AT, Odisho AY, Canes D. Harnessing generative artificial intelligence to improve efficiency among urologists: welcome ChatGPT. J Urol 2023 May;209(5):827-829 [ CrossRef ]
• Moons P, Van Bulck L. ChatGPT: can artificial intelligence language models be of value for cardiovascular nurses and allied health professionals. Eur J Cardiovasc Nurs 2023 Oct 19;22(7):e55-e59 [ CrossRef ] [ Medline ]
• Hosseini M, Horbach SPJM. Fighting reviewer fatigue or amplifying bias? Considerations and recommendations for use of ChatGPT and other large language models in scholarly peer review. Res Integr Peer Rev 2023 May 18;8(1):4 [ https://researchintegrityjournal.biomedcentral.com/articles/10.1186/s41073-023-00133-5 ] [ CrossRef ] [ Medline ]
• Rao A, Kim J, Kamineni M, Pang M, Lie W, Succi MD. Evaluating ChatGPT as an adjunct for radiologic decision-making. medRxiv. Preprint posted online Feb 7, 2023 [ https://doi.org/10.1101/2023.02.02.23285399 ] [ CrossRef ] [ Medline ]
• Ali SR, Dobbs TD, Hutchings HA, Whitaker IS. Using ChatGPT to write patient clinic letters. Lancet Digit Health 2023 Apr;5(4):e179-e181 [ https://linkinghub.elsevier.com/retrieve/pii/S2589-7500(23)00048-1 ] [ CrossRef ] [ Medline ]
• Johnson S, King A, Warner E, Aneja S, Kann B, Bylund C. Using ChatGPT to evaluate cancer myths and misconceptions: artificial intelligence and cancer information. JNCI Cancer Spectr 2023 Mar 01;7(2):a [ https://europepmc.org/abstract/MED/36929393 ] [ CrossRef ] [ Medline ]
• Schorrlepp M, Patzer K. ChatGPT in der hausarztpraxis: die künstliche intelligenz im check. MMW Fortschr Med 2023 Mar 24;165(6):12-16 [ CrossRef ] [ Medline ]
• Salvagno M, Taccone FS, Gerli AG. Can artificial intelligence help for scientific writing? Crit Care 2023 Feb 25;27(1):75 [ https://ccforum.biomedcentral.com/articles/10.1186/s13054-023-04380-2 ] [ CrossRef ] [ Medline ]
• Zheng H, Zhan H. ChatGPT in scientific writing: a cautionary tale. Am J Med 2023 Aug;136(8):725-726.e6 [ CrossRef ] [ Medline ]
• Baumgartner C. The potential impact of ChatGPT in clinical and translational medicine. Clin Transl Med 2023 Mar;13(3):e1206 [ https://europepmc.org/abstract/MED/36854881 ] [ CrossRef ] [ Medline ]
• Goodman RS, Patrinely JR, Osterman T, Wheless L, Johnson DB. On the cusp: Considering the impact of artificial intelligence language models in healthcare. Med 2023 Mar 10;4(3):139-140 [ CrossRef ] [ Medline ]
• Hallsworth JE, Udaondo Z, Pedrós-Alió C, Höfer J, Benison KC, Lloyd KG, et al. Scientific novelty beyond the experiment. Microb Biotechnol 2023 Jun 14;16(6):1131-1173 [ https://europepmc.org/abstract/MED/36786388 ] [ CrossRef ] [ Medline ]
• Dunn C, Hunter J, Steffes W, Whitney Z, Foss M, Mammino J, et al. Artificial intelligence-derived dermatology case reports are indistinguishable from those written by humans: A single-blinded observer study. J Am Acad Dermatol 2023 Aug;89(2):388-390 [ CrossRef ] [ Medline ]
• Andersen MZ, Fonnes S, Rosenberg J. Time from submission to publication varied widely for biomedical journals: a systematic review. Curr Med Res Opin 2021 Jun 06;37(6):985-993 [ CrossRef ] [ Medline ]
• Asaad M, Rajesh A, Banuelos J, Vyas KS, Tran NV. Time from submission to publication in plastic surgery journals: The story of accepted manuscripts. J Plast Reconstr Aesthet Surg 2020 Feb;73(2):383-390 [ CrossRef ]
• Sebo P, Fournier J, Maisonneuve H. Is statistician involvement as co-author associated with reduced time to publication of quantitative research in general medical journals? A bibliometric study. Fam Pract 2019 Jul 31;36(4):431-436 [ CrossRef ] [ Medline ]
• Joanna W. What's a good impact factor (ranking in 27 categories). SCI Journal. URL: https://www.scijournal.org/articles/good-impact-factor [accessed 2023-04-22]
• SWOT analysis. Wikipedia. URL: https://en.wikipedia.org/wiki/SWOT_analysis [accessed 2023-04-23]
• Dess DG, Lumpkin GT, Eisner AB, McNamara G, editors. The limitations of SWOT analysis. In: Strategic Management: Text and Cases. 6th edition. New York, NY: McGraw-Hill/Irwin; 2012:82
• Hill T, Westbrook R. SWOT analysis: It's time for a product recall. Long Range Plann 1997 Feb;30(1):46-52 [ CrossRef ]
• Koch AJ. SWOT does not need to be recalled: It needs to be enhanced. www.westga.edu. URL: https://www.westga.edu/~bquest/2000/swot1.html [accessed 2023-05-01]
• Chermack TJ, Kasshanna BK. The use and misuse of SWOT analysis and implications for HRD professionals. Hum Resour Dev Int 2007 Dec;10(4):383-399 [ CrossRef ]
• Stuart-Harris C. Epidemiology of influenza in man. Br Med Bull 1979 Jan;35(1):3-8 [ CrossRef ] [ Medline ]
• Huang J, Yeung AM, Kerr D, Klonoff DC. Using ChatGPT to predict the future of diabetes technology. J Diabetes Sci Technol 2023 May 17;17(3):853-854 [ CrossRef ] [ Medline ]
• Garg S. Top 30 ChatGPT alternatives that will blow your mind in 2023 (free and paid). Writesonic Blog. URL: https:/​/writesonic.​com/​blog/​chatgpt-alternatives/​#31-best-chatgpt-alternatives-for-your-to-choose-from, [accessed 2023-04-23]
• GPTZero alternatives. Sourceforge. URL: https://sourceforge.net/software/product/GPTZero/alternatives [accessed 2023-04-23]
• Gao C, Howard F, Markov N, Dyer E, Ramesh S, Luo Y, et al. Comparing scientific abstracts generated by ChatGPT to original abstracts using an artificial intelligence output detector, plagiarism detector, and blinded human reviewers. bioRxiv. Preprint posted online Dec 27, 2022 [ https://doi.org/10.1101/2022.12.23.521610 ] [ CrossRef ]
• Moltu C, Stefansen J, Svisdahl M, Veseth M. Negotiating the coresearcher mandate - service users' experiences of doing collaborative research on mental health. Disabil Rehabil 2012;34(19):1608-1616 [ CrossRef ] [ Medline ]
• Teixeira da Silva JA. Is ChatGPT a valid author? Nurse Educ Pract 2023 Mar;68:103600 [ CrossRef ]
• Siegerink B, Pet LA, Rosendaal FR, Schoones JW. ChatGPT as an author of academic papers is wrong and highlights the concepts of accountability and contributorship. Nurse Educ Pract 2023 Mar;68:103599 [ CrossRef ] [ Medline ]
• Zielinski C, Winker M, Aggarwal R. Chatbots, ChatGPT, and scholarly manuscripts. WAME recommendations on ChatGPT and chatbots in relation to scholarly publications. World Association of Medical Editors (WAME). URL: https://wame.org/page3.php?id=106 [accessed 2023-04-23]
• Defining the role of authors and contributors. International Committee of Medical Journal Editors (ICMJE). URL: https:/​/www.​icmje.org/​recommendations/​browse/​roles-and-responsibilities/​defining-the-role-of-authors-and-contributors.​html#two [accessed 2023-04-27]
• The use of AI and AI-assisted writing technologies in scientific writing. Elsevier. URL: https:/​/www.​elsevier.com/​about/​policies/​publishing-ethics/​the-use-of-ai-and-ai-assisted-writing-technologies-in-scientific-writing [accessed 2023-04-22]

Abbreviations

Edited by A Mavragani; submitted 26.05.23; peer-reviewed by DM Hirkani, J Glanville, M Succi; comments to author 05.09.23; revised version received 26.09.23; accepted 27.09.23; published 16.11.23

©Daniel Gödde, Sophia Nöhl, Carina Wolf, Yannick Rupert, Lukas Rimkus, Jan Ehlers, Frank Breuckmann, Timur Sellmann. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 16.11.2023.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.

Title: Literature review of agile manufacturing enablers for Indian manufacturing industry

Authors : Suchita P. Lokhande; Avinash D. Sarode

Addresses : Department of Mechanical Engineering, Lokmanya Tilak College of Engineering, Kopar Khairane, Navi Mumbai, India ' Department of Mechanical Engineering, Lokmanya Tilak College of Engineering, Kopar Khairane, Navi Mumbai, India

Abstract : In manufacturing sector, the medium scale industries play an important role for the Indian economy. There is a drastic change in customer demands posing a major challenge before the manufacturing industries. Agile manufacturing (AM) is a concept which incorporates customer issues in the traditional manufacturing process, lack of awareness about the use of AM needs the proper identification of enablers considering Indian scenario. Agility is the amalgamation of technology and management which is useful in the manufacturing sector, thus the use of scalable framework and integrated computer manufacturing is the need of an hour. Medium scale industries are not aware about AM; however, it will be appropriate if the Indian manufacturing industry also makes use of AM. For the implementation of AM in the Indian manufacturing industry, the most essential enablers are identified in this paper. A phase wise literature survey spanning from year 1995 to 2020; divided in three phases of seven, seven and nine year respectively, provided the focus on the enablers. From the in-depth literature review of 167 papers and discussion with experts, we have 85 sub-criteria with 12 categories of enablers.

Keywords : agile manufacturing; manufacturing industry; enablers; small and medium scale enterprises; SME.

DOI : 10.1504/IJSOM.2023.134803

International Journal of Services and Operations Management, 2023 Vol.46 No.3, pp.303 - 321

Received: 05 Dec 2020 Accepted: 05 Jun 2021 Published online: 13 Nov 2023 *

Keep up-to-date

• Our Newsletter ( subscribe for free )
• New issue alerts