On this page:
Dynamic search is JSTOR's AI-enabled search experience, designed to help researchers refine an initial query, identify relationships across sources and disciplines, and find related materials.
While a keyword search relies on exact matches to your search term(s), dynamic search mode surfaces content that is conceptually related to your query. This may help you find relevant content that may be missed in a traditional keyword search due to differences in terminology for the same subject.
For example, a dynamic search for “ecological resilience in urban planning” might also return results about “climate adaptation planning for cities” or “urban green infrastructure” as these concepts are contextually similar.
For information on JSTOR's approach to AI, visit JSTOR and AI.
Accessing dynamic search mode
To begin using dynamic search, you must be logged into a personal JSTOR account and paired to a participating institution.
- First, log in or register for a free personal JSTOR account.
- At this time, a personal account is required to access dynamic search mode.
- Next, ensure you're logged into JSTOR through your institution by checking the banner at the top of any page on JSTOR for your institution name.
- If you're not logged in through your institution, use the link in the banner to search for your institution and log in with your institutional credentials. See How to tell if you are logged in to JSTOR for more.
If JSTOR's AI tools have been enabled for your institution, you'll see the option to choose dynamic search mode in the primary search bar on JSTOR.
When performing a keyword search, you can also switch to dynamic search mode for your original query or click any of the suggested related searches to perform a new dynamic search.
About dynamic search results
When you perform a dynamic search, multiple parallel searches based on conceptually-similar terms are run, the results are ranked, and the strongest matches out of all available keyword-based matches on JSTOR are returned. The number of returned results will vary from query to query.
| Keyword search | Dynamic search | |
|---|---|---|
| How it works... |
Looks for exact matches between your search term(s) and an item’s metadata and content. Matches in an item’s Title and Author fields are weighted more heavily in terms of relevance. |
Runs parallel Boolean and semantic searches to return the strongest matches based on the conceptual similarity of your search query and an item’s content. Your exact search terms may or may not appear within the item itself. |
| Results include... | All academic and primary source content on JSTOR, including text, image, audio, and video content. | Journal articles, book chapters, and research reports only. |
| Refine your results with... |
Use Boolean operators (AND, OR, or NOT), exact phrase matching (quotation marks), wildcards, and proximity searching to construct your query. You can also search within specific fields such as Title, Author, or Publication. In addition, you can refine your results using the facets and filters in the Refine Results sidebar. See An Introduction to Searching on JSTOR for more information. |
You can modify or adjust your search query in the search bar at any time, or select any of the suggested related searches to narrow or broaden your original query. Semantic results do not support facets and filters found in the Refine Results sidebar; however, you’ll only be shown content that you can access. |
| Example search queries |
|
|
Suggested searches
Below the total number of search results, you'll see additional suggested searches based on your original query. Selecting any of these suggestions will perform a new dynamic search.
Select Show more suggestions to see additional related searches, as well as suggested searches to broaden or narrow the scope of your original query.
Previewing search results
You can preview any item in your search results without losing your place on the search results page. Select Quick preview next to any item to see the following information about each:
- How the item is related to your search
- What the item is about (or the publisher-provided abstract, if available)
- Topics covered in the item's full text
From the quick preview panel, you can also download, cite, or save the item to your personal workspace.
Results overview and Q&A
The Results overview panel appears alongside the search results and provides the following information about the results displayed:
- Overview and Themes - Concepts, key points, and themes from across your results set supported with inline citations to supporting sources.
- Publication dates - A timeline of your results by publication year.
- Authors - A list of authors represented in your results.
- Search results Q&A - Ask questions about your search results. Similar to asking questions about an item in the AI research tool, you can use natural language and don't need to word your request in the form of a question.
Selecting one or more themes, publication years, or authors will filter both your results set and the corresponding information in the results overview panel.
For example, you might select one or more authors from the Authors tab to filter your results to items by that author and highlight the relevant publication years and themes covered in their work.
Filtering your results set will also limit the scope of the search results Q&A to answers based on those results only.