Improved Performances and Motivation in Intelligent Tutoring Systems: Combining Machine Learning and Learner Choice

This paper presents a randomized controlled trial (265 students, ages 7-8) evaluating ZPDES, an AI-driven intelligent tutoring system that uses multi-armed bandit algorithms and the Learning Progress Hypothesis to personalize exercise sequencing, comparing conditions with and without learner choice against a hand-designed curriculum. The study measures both learning outcomes and intrinsic motivation, finding that adaptive personalization improves performance and that adding learner choice further enhances motivation and learning only when paired with adaptive systems.

Large class sizes challenge personalized learning in schools, prompting the use of educational technologies such as intelligent tutoring systems. To address this, we present an AI-driven personalization system, called ZPDES, based on the Learning Progress Hypothesis - modeling curiosity-driven learning - and multi-armed bandit techniques. It sequences exercises that maximize learning progress for each student. While previous studies demonstrated its efficacy in enhancing learning compared to han

Study Type

Source

Framework Categories

Tool Types

Tags