Clustering and Profiling Students According to their Interactions with an Intelligent Tutoring System Fostering Self-Regulated Learning


In this paper, we present the results obtained using a clustering algorithm (Expectation-Maximization) on datacollected from 106 college students learning about the circulatory system with MetaTutor, an agent-basedIntelligent Tutoring System (ITS) designed to foster self-regulated learning (SRL). The three extracted clusterswere validated and analyzed using multivariate statistics (MANOVAs) in order to characterize three distinctprofiles of students, displaying statistically significant differences over all 12 variables used for the clustersformation (including performance, use of note-taking and number of sub-goals attempted). We show throughadditional analyses that variations also exist between the clusters regarding prompts they received by the systemto perform SRL processes. We conclude with a discussion of implications for designing a more adaptive ITSbased on an identification of learners' profiles.

Full Text:



  • There are currently no refbacks.

Copyright (c) 2014 JEDM - Journal of Educational Data Mining