Predicting Student Dropout Risk Using LMS Logs
DOI:
https://doi.org/10.52731/lir.v004.226Keywords:
learning management system, log data, machine learning, prediction of at-risk studentAbstract
Traditionally, the prediction of student dropout in university classes has often been based on stu-dents’ pre-enrollment information or confirmed grade data for each semester after enrollment. However, effective support requires early intervention when signs of dropping out appear. In this study, we propose a model to continuously measure dropout signs using log data accumulated in a learning management system during classes. By applying machine learning to the log data in the learning management system, we could continuously update information on at-risk students with high accuracy from the beginning to the end of the class.
References
Ministry of Education, Culture, Sports, Science and Technology, https://www.mext.go.jp/en/index.htm (accessed 2023-10-23).
Tinto,V., “Dropout from Higher Education: A Theoretical Synthesis of Recent Research,” Re-view of Education Research, Vol.45, No.1, pp.89-125, 1975.
Tinto,V, “Classrooms as Communities: Exploring the Educational Character of Student Per-sistence,” The Journal of Higher Education, Vol.68, No.6, pp.599-623, 1997.
ASTIN, A.W., “Preventing students from dropping out, ” Jossey-Bass Inc Pub, San Francisco, 1975.
Robbins, S.B., Lauver, K., Le, H., Davis, D., Langley, R., Carlstrom, A., “Do Psychosocial and Study Skill Factors Predict College Outcomes? A Meta-Analysis,” Psychological Bulletin, Vol.130, No.2, pp.261-288, 2004.
Mangold,W.D., Bean,L.G.,Adams,D. J., Schwab,W.A.,Lynch,S.M., “Who Goes Who Stays: An Assessment of the Effect of a Freshman Mentoring and Unit Registration Program on College Persistence,” Journal of College Student Retention: Research, Theory & Practice, Vol.4, No.2, pp.95-122, 2002.
Brown, G. T. L., Peterson, E. R., & Yao, E. S. , “Student Conceptions of Feedback: Impact on Self-Regulation, Self Efficacy, and Academic Achievement.,” British Journal of Educa-tional Psychology,Vol. 86, pp.606-629, 2016.
Salmon,G., “E-moderating: The Key to Teaching and Learning Online,” Routledge, London, 2021.
Seidman,A. “College Student Retention: Formula for Student Success Second Edition,” Row-man & Littlefield Publishers. 2012.
Thomas, S. L., “Ties that Bind,” The Journal of Higher Education, Vol.71, No.5, pp.591-615, 2000.
Zimmerman, B.J., & Moylan, A.R. , “Self-Regulation: Where Metacognition and Motiva-tion Intersect.,” Handbook of Metacognition in Education, pp.299-316, 2009.
11 Oi, M., Okubo, F., Shimada, A., Yin, C., Ogata, H., “Analysis of Preview and Review Patterns in Undergraduates’ e-Book Logs,” Proceedings of the 23rd International Conference on Computers in Education, pp.166–171, 2015.
Akcapınar,G., Hasnine, M. N., Majumdar, R., Flanagan, B., & Ogata, H., “Developing an Early-Warning System for Spotting At-Risk Students by using eBook Interaction Logs,” Smart Learning Environments, Vol.6, No.4, pp.1–15, 2019.
Wan, H., Liu, K., Yu, Q., & Gao, X, “Pedagogical Intervention Practices: Improving Learn-ing Engagement based on Early Prediction,” IEEE Transactions on Learning Technologies, Vol.12, No.2, pp.278–289, 2019.
Flanagan,B., Majumdar,R. & Ogata, H., “Early-Warning Prediction of Student Performance and Engagement in Open Book Assessment by Reading Behavior Analysis,” Int J Educ Tech-nol High Educ, Vol.19,No.41, 2022.
Beaudoin, M. F., “Learning or lurking?: Tracking the “invisible” online student,” The Inter-net and Higher Education,Vol.5, No.2, pp.147–155, 2002.
Educational Technology Services - Blackboard, Blackboard.Inc, https://www.blackboard.com (accessed 2023-10-23).
The Snowflake Data Cloud - Mobilize Data, Apps, and AI, Snowflake Inc, https://www.snowflake.com/en/ (accessed 2023-10-23).
Kary.N, Philip.L, “A Lightweight Method using LightGBM Model with Optuna in MOOCs Dropout Prediction,” Proceedings of the 6th International Conference on Education and Mul-timedia Technology, pp.53-59, 2022.
Welcome to LightGBM’s documentation, Microsoft Corporation, https://lightgbm.readthedocs.io/en/v4.1.0/ (accessed 2023-10-23).
Kovanović, V., Gašević, D., Dawson, S., Joksimović, S., Baker, R. S., & Hatala, M., “Pene-trating the Black Box of Time-on-Task estimation,” Proceedings of the 5th International Con-ference on Learning Analytics and Knowledge, pp.184–193, 2015.
