JSTOR has developed an AI-powered interactive research tool, currently in beta, designed to enhance the research experience by providing functionalities such as custom summaries, recommended topics, related content, and a question-and-answer feature. This tool leverages advanced AI models, including OpenAI’s GPT-3.5 and smaller open-source models, to facilitate semantic searches and generate accurate, relevant responses based on the content of academic texts.
Benefits & outcomes
- Improved research efficiency, allowing users to accomplish tasks in a fraction of the time previously required.
- Enhanced engagement, with users spending more time on JSTOR and interacting more deeply with content.
- Democratization of research by making scholarly content more accessible to a broader audience, including novice researchers and students.
- Positive user feedback highlighting the tool’s ability to streamline the research process and reduce frustration
Notes & quotes
“I can do in a day what it used to take me four or five days… AI isn’t doing any of the intellectual work for me… It’s not thinking things for me; it’s showing me where to look.” – Faculty member.
“Honestly, time is everything… Wasted time and difficulty levels will go down significantly because of this.” – Student user.
The tool’s Q&A feature allows users to “talk to the document,” engaging in a conversational manner to extract information.
Transparency is maintained by linking back to the original text sections used to generate answers, ensuring users can verify the information provided.
Publisher / company: JSTOR / ITHAKA
Date of case study: 01/05/2025
Source: https://about.jstor.org/blog/ai-and-other-advanced-technologies-on-jstor-what-were-learning/