Modeling learning patterns of students with a tutoring system using Hidden Markov Models

Abstract

The current paper focuses on modeling actions of high school students with a mathematics tutoring system with Hidden Markov Models. The results indicated that including a hidden state estimate of learner engagement increased the accuracy and predictive power of the models, both within and across tutoring sessions. Groups of students with distinct engagement trajectories were identified, and findings were replicated in two independent samples. These results suggest that modeling learner engagement may help to increase the effectiveness of intelligent tutoring systems since it was observed that engagement trajectories were not predicted by prior math achievement of students.