Student Clustering Based on Learning Behavior Data in the Intelligent Tutoring System

Student Clustering Based on Learning Behavior Data in the Intelligent Tutoring System

Ines Šarić-Grgić (Faculty of Science, University of Split, Split, Croatia), Ani Grubišić (University of Split, Faculty of Science, Split, Croatia), Ljiljana Šerić (University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, Croatia) and Timothy J. Robinson (Department of Mathematics and Statistics, University of Wyoming, Laramie, USA)
Copyright: © 2020 |Pages: 17
DOI: 10.4018/IJDET.2020040105

Abstract

The idea of clustering students according to their online learning behavior has the potential of providing more adaptive scaffolding by the intelligent tutoring system itself or by a human teacher. With the aim of identifying student groups who would benefit from the same intervention in AC-ware Tutor, this research examined online learning behavior using 8 tracking variables: the total number of content pages seen in the learning process; the total number of concepts; the total online score; the total time spent online; the total number of logins; the stereotype after the initial test, the final stereotype, and the mean stereotype variability. The previous measures were used in a four-step analysis that consisted of data preprocessing, dimensionality reduction, the clustering, and the analysis of a posttest performance on a content proficiency exam. The results were also used to construct the decision tree in order to get a human-readable description of student clusters.
Article Preview
Top

Literature Review

As it was previously mentioned, there are several research studies that deal with data-driven student clustering according to online learning behavior.

Mojarad et al. (2018) investigated data-driven student profiling in a web-based, adaptive assessment and learning system (ALEKS). The study grouped students into a set of clusters using data from the first half of the semester and 6 key characteristics: the initial assessment score percentage, the total number of assessments, the average days between assessments, the number of days since the initial assessment was taken, an average percentage score increase between assessments, and students’ final assessment score percentage in ALEKS (taken at the end of the class). By using Mean shift and K-means clustering algorithms, 5 distinct profiles were identified: strugglers, average students, sprinters, gritty, and coasters. The researchers found these profiles to be useful in enabling institutions and teachers to identify students in need and for subsequently devising and implementing appropriate interventions for groups of students with similar characteristics.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 19: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 18: 4 Issues (2020)
Volume 17: 4 Issues (2019)
Volume 16: 4 Issues (2018)
Volume 15: 4 Issues (2017)
Volume 14: 4 Issues (2016)
Volume 13: 4 Issues (2015)
Volume 12: 4 Issues (2014)
Volume 11: 4 Issues (2013)
Volume 10: 4 Issues (2012)
Volume 9: 4 Issues (2011)
Volume 8: 4 Issues (2010)
Volume 7: 4 Issues (2009)
Volume 6: 4 Issues (2008)
Volume 5: 4 Issues (2007)
Volume 4: 4 Issues (2006)
Volume 3: 4 Issues (2005)
Volume 2: 4 Issues (2004)
Volume 1: 4 Issues (2003)
View Complete Journal Contents Listing