Home // DATA ANALYTICS 2015, The Fourth International Conference on Data Analytics // View article
Authors:
Il-Hyun Jo
Yeonjeong Park
Hyeyun Lee
Jongwoo Song
Suyeon Kang
Keywords: Learning Management System; Clustering analysis; Gaussian Mixture Model; K-Means clustering; Hierarchical clustering.
Abstract:
This study tried to find a group of academic courses based on the usage levels and patterns of Learning Management System (LMS) utilized in higher education using clustering techniques. LMS is an essential technology to support virtual learning environment where students access to the learning materials that their instructors provide, submit the deliverables, and participate in various learning activities involving group projects, discussion forums, quizzes, and Wikis. However, the returns on large investment have not systematically performed in terms of what extent of students and instructors have utilized the system for their teaching and learning. In this study, 2,639 courses opened during 2013 fall semester in a large private university located in South Korea were analyzed with 13 observation variables that represent the characteristics of academic courses. Three clustering methods including Gaussian Mixture Model(GMM), K-Means clustering, and Hierarchical clustering contributed to (1) identifying large number of courses that show inactive and no usage of LMS, (2) disclosing the dramatically imbalanced clusters, and (3) identifying several clusters that present different usage patterns of LMS. The results of such academic analytics provide meaningful implications for academic leaders and university staff to make strategic decisions on the development of LMS.
Pages: 130 to 137
Copyright: Copyright (c) IARIA, 2015
Publication date: July 19, 2015
Published in: conference
ISSN: 2308-4464
ISBN: 978-1-61208-423-7
Location: Nice, France
Dates: from July 19, 2015 to July 24, 2015