Improving Intelligent Tutoring Systems: Using Expectation Maximization to Learn Student Skill Levels

This paper describes research to analyze students’ initial skill level and to predict their hidden characteristics while working with an intelligent tutor. Based only on pre-test problems, a learned network was able to evaluate a students mastery of twelve geometry skills. This model will be used online by an Intelligent Tutoring System to dynamically determine a policy for individualizing selection of problems/hints, based on a students learning needs. Such knowledge is essential to the overall effectiveness of the tutor. Using Expectation Maximization, we learned the hidden parameters of several Bayesian networks that linked observed student actions (e.g. correct, incorrect or skipped answers on the pretest) with inferences about unobserved features (e.g. knowledge of specific skills). Bayesian Information Criterion was used to evaluate different skill models. The contribution of this work includes learning the parameters of the best network, whereas in previous work, the structure of a student model was fixed.