With
the popularity of online learning, the analysis of student learning behavior
and the prediction of academic performance have become a hot research topic in
the field of education. This study aims to analyze the factors influencing learning outcomes on online platforms,
extract the feature variables from online learning behavior, and
construct a weighted random forest model to predict
students’ online learning performance. Additionally, a method for computing feature importance is designed to analyze online learning behavior
based on the significance of different behavioral features. This contributes to
gaining early insights into students’ learning progress, proactively
identifying learning issues and strategically allocating educational resources,
thus providing students with enhanced guidance and support.
References
[1]
Arafiyah, R., Hasibuan, Z. A., & Santoso, H. B. (2020). Monitoring Online Learners Performance Based on Learning Progress Prediction. AIP Conference Proceedings, 2331, Article ID: 060012.
[2]
Breiman, L. (2001). Random Forests. Machine Learning, 45, 5-32.
https://doi.org/10.1023/A:1010933404324
[3]
Chen, W. Y., Brinton, C. G., Cao, D. et al. (2019). Early Detection Prediction of Learning Outcomes in Online Short-Courses via Learning Behaviors. IEEE Transactions on Learning Technologies, 12, 44-58. https://doi.org/10.1109/TLT.2018.2793193
[4]
Fan, L. (2019). Student Achievement Prediction Model Based on Big Data in the Context of Intelligent Education. China Computer & Communication, 24, 223-225.
[5]
Lee, C. A., Tzeng, J. W., Huang, N. F. et al. (2021). Prediction of Student Performance in Massive Open Online Courses Using Deep Learning System Based on Learning Behaviors. Educational Technology & Society, 24, 130-146.
[6]
Li, Y., Powell, S., Ma, H. et al. (2014). The Impact of MOOCs on Higher Education: A Perspective from Theory of Disruptive Innovation. Modern Distance Education Research, 55-59.
[7]
Liu, Y. G. (2020). Analysis and Research on Early Warning of College Students’ Achievements Based on Big Data. Digital Technology & Application, 38, 95-96.
[8]
Liu, Z. Y., Lomovtseva, N., & Korobeynikova, E. (2020). Online Learning Platforms: Reconstructing Modern Higher Education. International Journal of Emerging Technologies in Learning, 15, 4-21. https://doi.org/10.3991/ijet.v15i13.14645
[9]
Mi, H. C., Gao, Z. H., Zhang, Q. R. et al. (2022). Research on Constructing Online Learning Performance Prediction Model Combining Feature Selection and Neural Network. International Journal of Emerging Technologies in Learning, 17, 94-111.
https://doi.org/10.3991/ijet.v17i07.25587
[10]
Ren, Z. G., & Shang, F. H. (2019). Online Course Grade Prediction Model Based on Behavior Analysis. Computer Technology and Development, 29, 139-143.
[11]
Song, Y., Zhu, L. Q., & Cheng, Z. K. (2017). Research on Student Performance Evaluation Based on Random Forest. Journal of Qiqihar University (Natural Science Edition), 33, 1-5.
[12]
Wang, R. (2021). Research on Learning Achievement Prediction Based on PSO-BP Network. Journal of Anyang Normal University, 2, 41-45.
[13]
Xiao, Y. Z., Wang, P., Huang, C. Y. et al. (2019). Personalized Accurate Recommendation Analysis of Online Learning Content Based on Big Data. Microcomputer Applications, 35, 41-43.
[14]
Yu, X., & Zhou, Y. F. (2020). Research on Early Warning of College Students’ Achievements Based on Random forest Algorithm in the Context of Big Data. Jiangsu Science & Technology Information, 20, 50-53.
[15]
Zheng, A. Q., Wang, Y. Q., & Hao, C. Y. (2021). Research on Online Academic Achievement Prediction with Deep Learning. Computer Era, 12, 69-72.
