A partnership between two universities seeks to predict where students will struggle academically to help better inform instructor strategies
A method of analyzing what students post in academic forums, and using those posts to help instructors identify where students are struggling most with reading materials, could help improve learning and instruction.
Researchers at Ben-Gurion University of the Negev (BGU) and MIT are using a new method to analyze students’ online academic forum posts to predict questions so teachers can intervene.
The Nota Bene (NB) forum, developed by MIT Prof. David Karger, is a web-based collaborative annotation tool that supports communication among and between students and their instructors. It is currently in use by thousands of students in dozens of courses given worldwide.
Dr. Ya’akov “Kobi” Gal of BGU’s Department of Information Systems Engineering , and his student team, used machine learning to analyze student posts and predict what parts of the course presented the most trouble in course reading material. Dr. Gal and his students previously developed the first online plan recognition algorithm that has been empirically shown to make accurate predictions in students’ use of open-ended, forum-based educational environments.
The BGU team worked in Prof. Karger’s Computer Science and Artificial Intelligence Lab at MIT, mapping how the students interacted in the forum. Thread length found in a post was used as a metric for determining student confusion on a given topic.
“There were hundreds of thousands of comments in the forum, but no one was looking at how the students were using them,” says Dr. Gal, who is also head of BGU’s Human-Computer Decision-Making Lab. “By analyzing posts from previous courses, we can improve the education process. We are identifying the threads that will generate confusion ahead of time and making this information available to instructors.”
This project is part of the BGU- MIT International Science and Technology Initiative Seed Fund launched last year, which enables the faculty and scientists at the two universities to begin new research endeavors.
Material from a press release was used in this report.
- First-generation students are more likely to seriously consider leaving college - April 17, 2024
- How higher ed can meet workforce needs - April 15, 2024
- Higher ed leaders believe continuing education units are undervalued - April 10, 2024