Data Mining Applications to Online Learning
Jui-Long Hung, Texas Tech University, United States ; Ke Zhang, Wayne State University, United States
E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education, in Honolulu, Hawaii, USA ISBN 978-1-880094-60-0 Publisher: Association for the Advancement of Computing in Education (AACE), San Diego, CA
This study was intended to pilot the powerful potentials of data mining techniques in revealing students online learning behaviors and constructing and testing predictive models for online learning management, facilitation and improvement. 17,934 server logs were analyzed using statistical models and machine learning data mining techniques (Chen, Sakaguchi & Frolick, 2000; Tseng, Tsai, Su, Tseng & Wang, 2005) to reveal online learning behaviors of 99 undergraduate students in 6 weeks. The results revealed students' behavioral patterns and preference, identified active and passive learners and extracted important parameters for performance prediction. The results also demonstrated how data mining techniques could be utilized to help improve online teaching and learning. Practical implications on educational research and practice were discussed.
Hung, J.L. & Zhang, K. (2006). Data Mining Applications to Online Learning. In T. Reeves & S. Yamashita (Eds.), Proceedings of E-Learn 2006--World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education (pp. 2014-2021). Honolulu, Hawaii, USA: Association for the Advancement of Computing in Education (AACE).
© 2006 Association for the Advancement of Computing in Education (AACE)