Question Personalization in an Intelligent Tutoring System
This addresses the need for more effective personalized learning in educational technology, though it is incremental as it builds on prior dialogue-based personalization work by focusing on question phrasing.
The paper tackled the problem of personalizing question phrasing in intelligent tutoring systems to improve student learning outcomes, showing that generating question versions suitable for different proficiency levels increased learning gains through an A/B test with expert-written variants.
This paper investigates personalization in the field of intelligent tutoring systems (ITS). We hypothesize that personalization in the way questions are asked improves student learning outcomes. Previous work on dialogue-based ITS personalization has yet to address question phrasing. We show that generating versions of the questions suitable for students at different levels of subject proficiency improves student learning gains, using variants written by a domain expert and an experimental A/B test. This insight demonstrates that the linguistic realization of questions in an ITS affects the learning outcomes for students.