Clustering student performance data using k-means algorithms

Sultan Juma Sultan Alalawi; Izwan Nizal Mohd Shaharanee; Jastini Mohd Jamil

doi:10.32890/jcia2023.2.1.3

Authors

Sultan Juma Sultan Alalawi Ministry of Education Oman, Oman
Izwan Nizal Mohd Shaharanee Universiti Utara Malaysia, Malaysia https://orcid.org/0000-0002-3566-7257 (unauthenticated)
Jastini Mohd Jamil Universiti Utara Malaysia, Malaysia

DOI:

https://doi.org/10.32890/jcia2023.2.1.3

Keywords:

clustering, education data mining, k-means algorithm, student performance

Abstract

Education institutions store large amounts of data regarding students, such as demographics, academic-related data, and student activities. These data were recorded and stored in many ways, including different filing systems and database formats. By having these data, education institutions have a better way to manage and understand their students. In addition, information related to their students can easily be accessed and extracted. As more data is recorded and stored, this could allow the educational institution to make more informed decisions and give educators good insight into the educational system. The research approach known as educational data mining (EDM) focuses on using data mining techniques to extract massive data from the educational context and transform it into knowledge that can improve educational systems and decisions. Clustering, an unsupervised learning technique, is one of the most powerful machine- learning tools for discovering patterns and unseen data. This work aims to provide insights into the data obtained from Oman Education Portal (OEP) related to the student’s performance by manipulating the k-means algorithm.

References

Alashwal, H., El Halaby, M., Crouse, J. J., Abdalla, A., & Moustafa, A. A. (2019). The application of unsupervised clustering methods to Alzheimer’s disease. Frontiers in Computational Neuroscience, 13(May), 1–9. http://doi.org/10.3389/fncom.2019.00031

Alawi, S. J. S., Shaharanee, I. N. M., & Jamil, J. M. (2017). Profiling Oman education data using data mining approach. AIP Conference Proceedings, 1891. http://doi.org/10.1063/1.5005467

Beal, C. R., Qu, L., & Lee, H. (2006). Classifying learner engagement through integration of multiple data sources. Proceedings of the National Conference on Artificial Intelligence, 21(1), 151. http://www.aaai.org/Papers/AAAI/2006/AAAI06-024.pdf

Bernard, K. D. M. (2015). Comparative performance analysis of clustering techniques in educational. IADIS International Journal on Computer Science and Information Systems, 10(2), 65–78.

Darcan, O., & Badur, B. (2012). Student profiling on academic performance using cluster analysis. Journal of E-Learning & Higher Education, 2012, 1–8. http://doi.org/10.5171/2012.622480

Iam-On, N., & Boongoen, T. (2017). Generating descriptive model for student dropout: a review of clustering approach. Human-Centric Computing and Information Sciences, 7(1), 1–24. http://doi.org/10.1186/s13673-016-0083-0

International Labour Organization. (2012). Sultanate of Oman - Extension of the Decent Work Country Program. https://www.ilo.org/wcmsp5/groups/public/---arabstates/---ro-beirut/documents/genericdocument/wcms_446085.pdf

Kumar, A. D., & Radhika, V. (2014). A survey on predicting student performance. International Journal of Computer Science and Information Technologies, 5(5), 6147–6149.

Li, C., & Yoo, J. (2006). Modeling student online learning using clustering. Proceedings of the 44th Annual Southeast Regional Conference, 186-191. https://doi.org/10.1145/1185448.1185490

Nandakumar, A. N. (2018). An effective cure clustering algorithm in education data mining techniques to valuate student’s performance. International Journal of Applied Engineering Research, 13(10), 7493–7498.

National Centre for Statistics and Information. (2015). His Majesty Sultan Qaboos bin Said. Statical Year Book, (42).

Nelson, K. (2015). Using k -means clustering to model students LMS participation in traditional courses. Issues in Information Systems, 16(4), 16(Iv), 102–110.

Patil, C., & Baidari, I. (2019). Estimating the optimal number of clusters k in a dataset using data depth. Data Science and Engineering, 4(2), 132–140. http://doi.org/10.1007/s41019-019-0091-y

Trivedi, S., Pardos, Z., Sárközy, G., & Heffernan, N. (2011). Spectral clustering in educational data mining. Proceedings of the 4th International Conference on Educational Data Mining, 129–138.