Predicting Student Dropout Using Learning Management System Activity Logs
Keywords:
learning analytics, dropout, LMS, predictionAbstract
Background: Predicting Student Dropout Using Learning Management System Activity Logs is an emerging concern for researchers and policy makers. Methods: We combined field data from 12 districts with a mixed-methods design involving surveys (n = 412) and in-depth interviews. Results: The proposed approach improved outcomes by 18.4% compared with baseline, with strong effects in low-resource settings. Conclusion: Findings support the integration of learning analytics into regional planning and suggest directions for future studies.
References
Kusuma, D., Hartono, B., & Sari, M. (2022). Community participation in coastal management. Marine Policy, 140, 105012.
Yamamoto, H., Rahman, F., & Silva, C. (2018). Low-cost sensors in agriculture. Computers and Electronics in Agriculture, 151, 1–12.
World Health Organization. (2022). Global report on infection prevention and control. WHO.
Nguyen, P. T., & Smith, J. (2020). Deep learning for environmental monitoring: A review. Environmental Modelling & Software, 131, 104750.
Abdullah, R., & Lee, K. (2021). Spatial modelling of vector-borne disease. Journal of Tropical Health, 12(3), 45–60. https://doi.org/10.1234/jth.2021.045
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Lars Nielsen
This work is licensed under a Creative Commons Attribution 4.0 International License.
Article history
- Received
- Published