Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 04014 | |
Number of page(s) | 6 | |
Section | AI and Advanced Applications | |
DOI | https://doi.org/10.1051/itmconf/20257004014 | |
Published online | 23 January 2025 |
Machine Learning Based Engagement Prediction for Online Courses
Qingdao University of Science and Technology, Department of Information Sciences and Technology, 266061 No. 99 Songling Road, Qingdao, Shandong Province, China
Corresponding author: mhinkle75096@student.napavalley.edu
Within the constraints of the epidemic, the demand for distance learning in education is growing rapidly, and technological advances are opening up new possibilities for online education. This study investigates the performance of three machine learning models (decision trees. SVMs, and random forests) in predicting online course participation. To ensure the accuracy and generalizability of the results, the paper evaluated the models using k-fold cross-validation. Performance metrics such as accuracy, precision, recall and F1 score were used for comparison. The results show that the Random Forest model outperforms the other models on all metrics while the SVM model performs the weakest among the three models. Therefore, this study conducted a feature importance analysis specifically for the decision tree and random forest models to gain insight into the predictive power of individual features. This helps educators and course designers to develop strategies to improve engagement and retention. In summary, this study emphasizes the effectiveness of random forests in predicting engagement in online courses and highlights the potential of machine learning in improving the quality of e-learning environments. The findings can help optimize ongoing online education discussions and can guide future research in the field of e-learning.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.