Stage-Dependent Behavioral Patterns in MOOC Dropout: An Explainable Learning Analytics Study
Open Access
- 24 June 2026
- journal article
- research article
- Published by MDPI AG in Education Sciences
- Vol. 16 (7) , 999
Abstract
The high dropout rate in massive open online courses (MOOCs) continues to limit their potential in promoting inclusive and sustainable learning. Although many prediction models have been used to identify potential dropouts, most studies view dropout as a static classification problem and fail to clearly reveal the dynamic trajectory of learner participation over time. Therefore, this study introduces a phased analysis perspective, treating MOOC dropout as a process that continuously evolves at different stages. On the basis of the KDDCUP2015 dataset, we constructed behavioral characteristics at three time points: the first week, the third week, and the fifth week. By combining robust feature analysis and interpretable models, we systematically examined the changing patterns of dropout modes. The results revealed significant differences across the different stages. In the early stage of the course, dropout was related mainly to the unstable interaction behaviors of learners, such as restricted access to resources and irregular participation rhythms. In the middle and late stages, task-oriented behaviors, especially those related to video-based learning activities, gradually became key factors. Notably, high-frequency video participation does not always reduce the risk of dropout; when video activity is high but the overall interaction rate is low, it is more likely to indicate an increase in the risk of dropout. These results indicate that the combination of behaviors is more crucial than mere activity levels. By revealing the changing characteristics of behaviors at different stages, this study helps support the design of more practical early warning methods.Keywords
Funding Information
- Chongqing Higher Education Teaching Reform Research Project (243051)
- Major Project for Undergraduate Teaching Reform Research in Higher Education of Chongqing (251017)
This publication has 53 references indexed in Scilit:
- Students’ Adaption of Progression Following Quiz Feedback Predicts Exam SuccessTechnology, Knowledge and Learning, 2025
- Soft adaptive node-level stabilization (SANLS): enhancing decision tree stability with information gain optimization and advanced splitting criteriaInternational Journal of Data Science and Analytics, 2025
- Ineffective Methods Lead to Wasted Effort: Learning Strategies Are More Important Than Student Engagement in Predicting Academic AchievementPsychology in the Schools, 2025
- Specialized Purpose of Each Type of Student Engagement: A Meta-AnalysisEducational Psychology Review, 2025
- Student adaptivity classification in online education through stacked ensemble learningMultimedia Tools and Applications, 2024
- Evaluating the student performance prediction and action framework through a learning analytics intervention studyEducation and Information Technologies, 2024
- Classification-driven intelligent system for automated evaluation of higher education exam paper qualityEducation and Information Technologies, 2024
- A review of random forest-based feature selection methods for data science education and applicationsInternational Journal of Data Science and Analytics, 2024
- Investigating Demographics and Behavioral Engagement Associated with Online Learning Performance2023
- Predictive modelling and analytics of students’ grades using machine learning algorithmsEducation and Information Technologies, 2022