An approach for analyzing student performance based on formative assessment scores using the k-means method
List of Authors
  • Malayphone Sonephachanh , Naoki Ohshima

Keyword
  • K-Means Method, Elbow Method, Formative Assessment, Learning Behavior Analysis

Abstract
  • This study aimed to analyze students' learning outcomes and behavioural tendencies using formative assessment scores for students enrolled in the "Research and Development Strategy" course offered at the Graduate School of Frontier Sciences, Yamaguchi University. This analysis aimed to gain detailed insight into individual students' understanding and learning behaviours in the educational process. An unsupervised machine learning algorithm combining the k-means and elbow methods was used in this study to classify student performance and tendencies effectively. The method revealed different aspects of students' learning behaviours and abilities, indicating its potential to improve the quality of education. This study applied a data-driven approach to educational analysis and provided an effective means of understanding the student learning process. The study results revealed that students in certain clusters exhibit specific performance characteristics and provide a basis for educators to obtain specific information to provide more appropriate instruction and support for individual students and groups of students. This approach also applies to other educational settings and subjects, contributing to improved student learning processes and outcomes. Furthermore, this study demonstrates the utility of a data-driven approach to educational analysis to be developed further in future studies.

Reference
  • 1. Dai, X., Erkkilä, T., Yli-Harja, O., & Lähdesmäki, H. (2009). A joint finite mixture model for clustering genes from independent Gaussian and beta distributed data. BMC bioinformatics, 10, 1-16. https://doi.org/Doi:10.1186/1471-2105-10-165

    2. Goh, Y. L., Goh, Y. H., Yip, C.-C., Ting, C. H., Bin, R. L. L., & Chen, K. P. (2020). Prediction of students' academic performance by K-means clustering. Science Proceedings Series, 2(1), 1-6.

    3. Lu, J.-F., Tang, J., Tang, Z.-M., & Yang, J.-Y. (2008). Hierarchical initialization approach for K-Means clustering. Pattern Recognition Letters, 29(6), 787-795. https://doi.org/10.1016/j.patrec.2007.12.009

    4. Luo, Y., Zhu, X., & Long, J. (2019). Data collection through mobile vehicles in edge network of smart city. IEEE access, 7, 168467-168483.

    5. MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. Proceedings of the fifth Berkeley symposium on mathematical statistics and probability,

    6. MacQueen, J. B. (1965). On the Asymptotic Behavior of k-means. Defense Technical Information Center, 10. https://doi.org/DOI: 10.21236/AD0629518

    7. Maheswari, K. (2019). Finding best possible number of clusters using k-means algorithm. International Journal of Engineering and Advanced Technology, 9(1S3), 533-538.

    8. Nanda, S., Mahanty, B., & Tiwari, M. (2010). Clustering Indian stock market data for portfolio management. Expert Systems with Applications, 37(12), 8793-8798. https://doi.org/10.1016/j.eswa.2010.06.026

    9. Nidheesh, N., Nazeer, K. A., & Ameer, P. (2017). An enhanced deterministic K-Means clustering algorithm for cancer subtype prediction from gene expression data. Computers in biology and medicine, 91, 213-221. https://doi.org/10.1016/j.compbiomed.2017.10.014

    10. Priebe, C. E., Park, Y., Vogelstein, J. T., Conroy, J. M., Lyzinski, V., Tang, M., Athreya, A., Cape, J., & Bridgeford, E. (2019). On a two-truths phenomenon in spectral graph clustering. Proceedings of the National Academy of Sciences, 116(13), 5995-6000. https://doi.org/10.1073/pnas.1814462116

    11. Rahman, M. A., & Islam, M. Z. (2014). A hybrid clustering technique combining a novel genetic algorithm with K-Means. Knowledge-Based Systems, 71, 345-365. https://doi.org/10.1016/j.knosys.2014.08.011

    12. Raykov, Y. P., Boukouvalas, A., Baig, F., & Little, M. A. (2016). What to do when K-means clustering fails: a simple yet principled alternative algorithm. Plos one, 11(9), e0162259. https://doi.org/10.1371/journal.pone.0162259

    13. Sinaga, K. P., & Yang, M.-S. (2020). Unsupervised K-means clustering algorithm. IEEE access, 8, 80716-80727.

    14. Syakur, M., Khotimah, B., Rochman, E., & Satoto, B. D. (2018). Integration k-means clustering method and elbow method for identification of the best customer profile cluster. IOP conference series: materials science and engineering,