Let AI Assist boost your literature review and analysis
As you may have noticed, there is a rapid growth in AI-based tools for all types of software packages. We followed this trend by releasing AI Assist – your virtual research assistant that simplifies your qualitative data analysis. In the following, we will present you the tools and functions of AI Assist and how they can facilitate your literature reviews.
Literature reviews are an important step in the data analysis journey of many research projects, but often it is a time-consuming and arduous affair. Whether you are reviewing literature for writing a meta-analysis or for the background section of your thesis, work with MAXQDA! Besides the classic tools of MAXQDA that can facilitate each phase of your literature review, the new tool AI Assist can boost your literature review and analysis in multiple ways.
How to use AI Assist for your literature review
Year by year, the number of publications grows in almost every field of research - our insights and knowledge likewise. The drawback is that the number of publications might be too high to keep track of the recent developments in your field of research. Consequently, conducting a proper literature review becomes more and more difficult, and the importance of quickly identifying whether a publication is interesting for your research question constantly increases.
Luckily, MAXQDA’s AI Assist tool is here to help. Among others, it can summarize your documents, text segments, and coded segments. But there is more – based on your coded segments AI Assist can generate subcodes suggestions. In the following, we will present you step-by-step instructions on how to use MAXQDA for your literature review and analysis with a special focus on how AI Assist can support you.
Step one of AI for literature reviews: Identify and import your literature
Despite the fact that MAXQDA and AI Assist can facilitate your literature review and analysis in manifold ways, the best advice is to carefully plan your literature review. Think about the purpose of your literature review and the questions you want to answer. Develop a search strategy which includes, but is not limited to, deciding on literature databases, search terms, and practical and methodological criteria for selecting high-quality scientific literature. Begin by searching the identified databases. Then briefly scan the search results for relevance by reading the title, keywords and abstract. If you find the publication interesting, download the PDF and bibliographic information (RIS), and let AI Assist help you determining whether the publication falls within the narrower area of your research question.
MAXQDA's import tab offers dedicated options for different data types. To import the selected literature, just click on the corresponding button, select the data you want to import, and click okay. Alternatively, you can import data simply by drag-and-dropping the data files from your Windows Explorer/Mac Finder window. If you import full texts and the corresponding bibliographic data, MAXQDA automatically connects the full text to the literature entry with an internal link.
Step two of AI for literature reviews: Determine a paper's relevance with AI Summaries and the AI Chat
After importing publications that might be relevant to your research question, you need to determine which ones truly merit inclusion in your review. AI Assist can dramatically accelerate this process by generating comprehensive document summaries on which you can base your decision about a paper's relevance.
To create an AI document summary, access the document's context menu and select AI Assist > Document Summary. Choose your desired summary language and length, then provide specialized instructions to focus the summary. For example, you can instruct the AI to focus the summary on thdories mentioned in the study or to highlight findings related to a specific research question. The AI-generated summary will be stored in a document memo where you can view and edit it as needed. In case you are not satisfied with the result, you might want to improve the instructions and try again. It's important to note that AI-generated summaries aren't perfect. When in doubt about a publication's relevance, it's advisable to read the entire paper.
Chat with your literature
With AI Assist's "Chat with This Document" feature, finding information and exploring aspects of your publication in detail becomes a breeze. You can access the AI-powered chat via a document's context menu. For example, you could ask the generative AI if the publication fulfills a specific criterion or if (and where) the publication includes a particular piece of information. Using the chat feature, you can resolve doubts about inclusion criteria and answer open questions that you might have regarding the literature's relevance. More ideas on what to ask the AI Chat can be found in our blog article.
Step three of AI for literature reviews: Sort and paraphrase your literature
Depending on the volume of publications in your MAXQDA project, you'll likely want to organize your documents in meaningful ways. Create document groups by clicking the respective icon in the Document System window and add documents via drag-and-drop. Alternatively, create Document Sets, which are especially helpful when sorting documents across multiple domains such as by relevance and methodology used.
While AI can support various stages of your literature review, it can't replace your deep understanding of the material. Many researchers create paraphrases when reviewing texts to summarize content in their own words—a practice particularly helpful when writing literature review reports.
To create AI-assisted paraphrases, highlight a text segment and select AI Assist > Paraphrase Selected Text from the context menu. Choose your desired language and paraphrase length, then edit the generated paraphrase in the provided text field to match your needs. Paraphrases appear in the Document window sidebar. If you don't see them immediately, click "Show sidebar" in the Document Browser's toolbar, right-click in the sidebar, and select "Paraphrase" from the context menu.
Step four of AI for literature reviews: AI Code your data
With MAXQDA, you can code your data either manually or use AI Assist to accelerate the process. A code serves as a label for phenomena in a text or image. Regardless of your coding approach, you'll need to create codes. Go to the Codes window and click the green plus icon. Choose a descriptive name, select a color, and write a code description. For AI coding, the description is crucial as it tells the AI what to look for. A precise code description also helps maintain consistency, especially when working in a team.
To use AI for coding, select AI Assist > AI Coding from a document's context menu. Drag and drop the relevant code into the dialogue and click okay to let AI Assist analyze the document and find text segments matching your code description. When complete, you'll receive a notification indicating how many segments were coded. If the results aren't satisfactory (too many or too few segments), consider adjusting your code description and repeating the process.
For research transparency, AI-generated codes are clearly distinguishable by their color and naming convention (code names always include the prefix "AI"). Additionally, AI Assist provides an explanation for each coding decision in the form of a coding comment, making it easy to follow the AI's reasoning and decide whether you agree. These comments are visible in the Document Browser's sidebar.
More tips and tricks on how to use AI Assist for the coding process can be found in our blog post.
Step five of AI for literature reviews: Refine your code system with AI-generated Subcode Suggestions
You can also perform initial coding manually and leverage AI Assist at later stages of your research process. For example, if you've applied broad codes to your data, you might wish to refine them into more precise subcodes.
To generate AI-assisted subcode suggestions, open the context menu of a code and choose AI Assist > Suggest Subcodes. Select your preferred language and optionally, request that AI Assist include examples for each subcode as a bullet list. The code suggestions will be stored in the code's memo. If you're satisfied with them, you can create and apply them to your data, either manually or using AI Coding as described in Step 4.
Step six of AI for literature reviews: Aggregate your literature review results
Once you've coded and/or paraphrased your data, it's time to aggregate your results. AI Assist offers several options for this final stage. If you've paraphrased the literature, you can summarize the paraphrases of a document using AI Assist. Navigate to the AI Assist tab, select the option "Summarize Paraphrases", and the AI-generated summary will be stored as a Document Memo. This approach is particularly useful when creating summaries at the document level.
For topic-related summaries, you can summarize the coded segments of a particular code. For example, summarize how "happiness" was operationalized across different studies. Access this feature from the AI Assist tab or the context menu of a code and the AI-generated summary will be stored as a code memo. If you've used a code multiple times in the same document, use the Summary Grid to summarize these multiple occurrences. Open the Summary Grid window, click the AI Assist icon, and follow the prompts to generate your summary.
From here, you can continue your analysis with MAXQDA's Overview and Summary Tables to further aggregate your results. Create visual representations of your data using MAXQDA's Visualization Tools and synthesize your findings with the Questions-Themes-Theories tool to write up your literature review or report.
Literature about literature reviews and analysis
We offer a variety of free learning materials to help you get started with your literature review. Check out our Getting Started Guide to get a quick overview of MAXQDA and step-by-step instructions on setting up your software and creating your first project with your brand new QDA software. In addition, the free Literature Reviews Guide explains how to conduct a literature review with MAXQDA in more detail.
