Discovering Unproductive Learning Patterns of Wheel-spinning Students in Intelligent Tutors Using Cluster Analysis

Abstract

Wheel-spinning is unproductive persistence without the mastery of skills. Understanding wheel-spinning during the use of intelligent tutoring systems (ITSs) is crucial to help improve productivity and learning. In this study, following Beck and Gong (2013), we defined wheel-spinning students (unsuccessful students in ITSs) as those who practiced the same skill set over 10 times but failed to submit correct answers three times in a row. The t-SNE and K-means clustering algorithms were used to probe wheel-spinning learning patterns. Our results showed three types of wheel-spinning patterns when using ASSISTments, an online mathematics tutoring system. The findings indicate that a lack of motivation, math knowledge, or metacognitive ability can cause the failure to learn math with ITSs, which provides us with a deeper understanding of students' failure in ITSs and clues about how we can help these unsuccessful students in ITSs.