On Semi-supervised Learning with Sparse Data Handling for Educational Data Classification
An educational data classification task at the program level is investigated in this paper. This task concentrates on predicting the final study status of each student from the second year to the fourth year in their study path. By doing that, in-trouble students can be predicted as soon as possible. However, the task faces two main problems. The first problem is the existence of incomplete data once we conduct an early prediction and the second one is the lack of labeled data for a supervised learning process of this task. In order to overcome those difficulties, our work proposes a robust semi-supervised learning method with sparse data handling in either sequential or iterative approach. The sparse data handling process can help us with the k-nearest neighbors-based data imputation and the semi-supervised learning process with a random forest model as a base learner can exploit the availability of a larger set of unlabeled data in the task. These two processes can be conducted in sequence or integrated in each other for robustness and effectiveness in educational data classification. The experimental results show that our resulting robust random forest-based self-training algorithm with the iterative approach to sparse data handling outperforms the other algorithms with different sequential and traditional approaches for conducting the task. This algorithm provides us with a more effective classifier as a practical solution on educational data over the time.
KeywordsSelf-training Random forest Educational data classification Sparse data K-Nearest neighbors
This research is funded by Vietnam National University Ho Chi Minh City, Vietnam, under grant number C2017-20-18.
- 1.Academic Affairs Office, Ho Chi Minh City University of Technology, Vietnam. http://www.aao.hcmut.edu.vn. Accessed 29 June 2017
- 2.Bayer, J., Bydzovska, H., Geryk, J., Obsivac, T., Popelinsky, L.: Predicting drop-out from social behaviour of students. In Proceedings of the 5th International Conference on Educational Data Mining, pp. 103–109 (2012)Google Scholar
- 8.Kostopoulos, G., Kotsiantis, S., Pintelas, P.: Estimating student dropout in distance higher education using semi-supervised techniques. In: Proceedings of the 19th Panhellenic Conference on Informatics, pp. 38–43 (2015)Google Scholar
- 14.Saarela, M., Karkkainen, T.: Analysing Student Performance using Sparse Data of Core Bachelor Courses. Journal of Educational Data Mining 7(1), 3–32 (2015)Google Scholar
- 15.Tanha, J., Someren, M., Afsarmanesh, H.: Semi-supervised self-training for decision tree classifier. Int. J. Mach. Learn. Cyber., 1–16 (2015). doi: 10.1007/s13042-015-0328-7
- 16.Taruna, S., Pandey, M.: An empirical analysis of classification techniques for predicting academic performance. In: Proceedings of the IEEE International Advance Computing Conference, pp. 523–528 (2014)Google Scholar
- 19.Weka 3, Data Mining Software in Java. http://www.cs.waikato.ac.nz/ml/weka. Accessed 28 June 2017
- 20.Yarowsky, D.: Unsupervised word sense disambiguation rivaling supervised methods. In: Proceedings the 33rd Annual Meeting of the Association for Computational Linguistics, pp. 189–196 (1995)Google Scholar