Reproduce “Question Personalization in an Intelligent Tutoring System” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sabina Elkins, Robert Belfer, Ekaterina Kochmar, Iulian Serban, Jackie C.K. Cheung
Researchers investigated whether adapting question phrasing in an intelligent tutoring system to a student's proficiency level impacts learning outcomes. Personalized question phrasing led to improved solution acceptance and reduced failure rates, with beginner students showing a 19% decrease in ultimate failure rate.
Key insights
- Aligning question phrasing with a student's predicted proficiency significantly improves learning outcomes, as evidenced by higher solution acceptance and lower ultimate failure rates.
- Personalized question phrasing acts as a valuable dimension of ITS personalization, extending beyond content selection to the subtle linguistic presentation of material.
- Beginner students benefit most from personalized question phrasing, suggesting it helps guide them within their zone of proximal development and enhances engagement.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.