On this page:
JSTOR’s interactive research tool uses AI and other technologies to help people work more efficiently and effectively. If enabled, this beta feature will appear on the item page for journal articles, book chapters, and research reports, and as a search option in addition to JSTOR’s standard keyword search.
The tool is in active development so new features and improvements are frequently added. For more information on how the tool is powered and JSTOR’s approach to generative AI, check out our FAQs.
Requesting access to the research tool beta
You can volunteer to participate in beta testing through the JSTOR platform. Users who are signed into a personal account and have institutional authentication on JSTOR will be shown a pop-up that asks if they would like to sign up to try the tool.
To sign up to participate in the beta:
- Visit www.jstor.org and log in to your personal JSTOR account.
- Don’t have an account yet? See how to register for a free account.
- Confirm you’re logged in to your school or institution by looking for your institution’s name at the top of the page. See how to tell if you’re logged in to JSTOR.
- When the sign-up window appears, click the Sign up button.
- If you just created your account, it may take up to five minutes for the window to display. Try coming back in a few minutes.
- Clicking the No thanks option will permanently dismiss the sign-up window.
Not seeing the sign-up window? You can also submit your interest via our sign-up form using the email address associated with your personal JSTOR account.
Please note, while we’re not able to provide a timeframe for access to the tool, we’ll notify you if and when access to the pre-release features becomes available for you to explore.
Searching for content
Participants in the interactive research tool beta will see an additional Experimental BETA search option on your JSTOR search results page. While JSTOR’s standard search relies on keyword matching, this option gives better results for natural language queries, similar to what you might enter into a Google search.
You’ll be shown the 25 most-relevant journal articles, book chapters, and/or research reports based on your query. Please note, while it’s not possible to refine your results using this search method, you’ll only be shown content that you can access.
At any time, you can toggle between JSTOR’s standard Keyword search and the Experimental BETA search by using the buttons at the top of your search results.
Evaluating and exploring content
Once you select an eligible text item from your search results, the research tool will start by identifying how your search query relates to the content by asking: “How is [your search query] related to this text?”
From here, you can continue evaluating the content through the research tool window or from the text itself.
Using prompts
You can learn more about the text as a whole by choosing one of the prompts provided by the research tool or by supplying your own. Read more about these options in the following chart.
Prompt | Description |
Summarize | Suggests the text’s key points and arguments, which can help determine its relevance to your inquiry. |
Recommend topics |
Suggests key concepts that are relevant to the text, which can provide ideas for further exploration. Clicking any of the suggested topics will perform a search in a new tab. |
Show related content |
Suggests items that contain similarities in text, which supports discovery and exploration. Note that these may differ from the “Related text” suggestions available under the document viewer, which are based on usage patterns. |
Ask a question |
Type your question in the chat box. The interactive research tool will only answer questions based on the content of the item itself. For example, if the text does not explicitly state that an article is peer reviewed, the tool cannot answer the question, “Is this document peer reviewed?” See JSTOR Research Tool (Beta): Asking Questions About a Text for more information and example questions. |
Using the text
You can learn more about a specific phrase or passage in the text by highlighting it in the document viewer and choosing one of the following options:
- Find related content - Suggests the top 5 items on JSTOR related to the selected text (up to 1,000 characters), with the option to see more results
- Summarize - Suggests the key points of the selected text (1,000 - 6,000 characters)