CLUSTERING SISWA BERDASARKAN MINAT DAN KEMAMPUAN UNTUK REKOMENDASI EKSTRAKULIKULER MENGGUNAKAN  ALGORITMA K-MEANS

Rina .; Nana Suarna; Agus Bahtiar; Cep Lukman Rohmat

Authors

Rina . STMIK IKMI Cirebon, Indonesia
Nana Suarna STMIK IKMI Cirebon, Indonesia
Agus Bahtiar STMIK IKMI Cirebon, Indonesia
Cep Lukman Rohmat STMIK IKMI Cirebon, Indonesia

Keywords:

K-Means, Clustering, Data Mining, Ekstrakurikuler

Abstract

Penentuan kegiatan ekstrakurikuler yang sesuai dengan minat dan kemampuan siswa merupakan faktor penting dalam mendukung pengembangan potensi siswa, namun proses pemilihannya sering kali masih dilakukan secara subjektif dan belum berbasis data. Penelitian ini bertujuan untuk menerapkan algoritma K-Means guna mengelompokkan siswa di SMK Al-Ma’rifah berdasarkan minat dan kemampuan dalam memilih kegiatan ekstrakurikuler.Penelitian ini menggunakan pendekatan data mining dengan teknik clustering menggunakan algoritma K-Means. Data penelitian diperoleh dari 120 siswa aktif dan dievaluasi pada lima dimensi utama, yaitu: akademik, olahraga, seni, keagamaan, dan sosial. Tahapan pemrosesan data meliputi tahap preprocessing melalui normalisasi menggunakan StandardScaler, penentuan jumlah cluster optimal dengan metode Elbow dan Silhouette Score, serta pengelompokan data menggunakan Python.Hasil penelitian menunjukkan bahwa jumlah cluster yang paling optimal adalah tiga cluster. Evaluasi model menghasilkan nilai Silhouette Score sebesar 0,1587 yang menunjukkan bahwa model mampu membentuk segmentasi siswa meskipun masih terdapat tumpang tindih antar-cluster. Proses clustering menghasilkan tiga profil utama, yaitu: kelompok dengan dominasi minat keagamaan dan sosial (Cluster 0), kelompok dengan kecenderungan pada seni dan akademik (Cluster 1), serta kelompok dengan minat tinggi pada olahraga dan kepemimpinan sosial (Cluster 2).Hasil pengelompokan ini memberikan gambaran pola minat dan kemampuan siswa yang nyata dan dapat digunakan sebagai dasar yang objektif. Pihak sekolah dapat menggunakan model ini untuk memberikan rekomendasi kegiatan ekstrakurikuler yang lebih sesuai dengan potensi siswa, sehingga mendukung pengambilan keputusan yang lebih terarah dan berbasis data.

References

Abdullah, M., Rahman, S., & Lestari, V. (2023). Enhanced Extracurricular Interest Grouping Using K-Means++ Clustering. Journal of Educational Informatics, 8(2), 55–67.

Aljohani, N. R., Fayoumi, A., & Hassan, S.-U. (2021). A framework for educational data mining using K-Means clustering for student grouping in e-learning systems. IEEE Access, 9, 146963–146972. https://doi.org/10.1109/ACCESS.2021.3123824

Balaguer, Á., Benítez, E., Albertos, A., Lara, S., & [others]. (2020). Not everything helps the same for everyone: Relevance of extracurricular activities for academic achievement. Humanities and Social Sciences Communications, 7, Article 79. https://doi.org/10.1057/s41599-020-00573-0

Bhardwaj, R., Jain, P., & Sharma, S. (2023). Comparative evaluation of clustering algorithms in educational data mining: A systematic review. IEEE Access, 11, 45812–45829. https://doi.org/10.1109/ACCESS.2023.3271845

Chen, L. (2021a). [Selected Reference]. [Unknown Journal].

Chen, L. (2021b). Student interest modeling using learning analytics and clustering algorithms. International Journal of Educational Technology, 18(4), 233–249.

Cortellazzo, L., Bruni, E., & Zampieri, A. (2021a). Experiences that matter: Unraveling the link between extracurricular activities and emotional and social competencies. Frontiers in Psychology, 12, Article 659526. https://doi.org/10.3389/fpsyg.2021.659526

Cortellazzo, L., Bruni, E., & Zampieri, R. (2021b). Social and religious extracurricular activities and their impact on students’ interpersonal competencies. Journal of Youth and Adolescence, 50(8), 1472–1488.

Jena, L., Panda, M., & Sahoo, S. (2023). Hybrid K-Means and deep learning framework for student performance analytics in higher education. Computers and Education: Artificial Intelligence, 4, 100099. https://doi.org/10.1016/j.caeai.2023.100099

Kaddoura, S., Popescu, D. E., & Hemanth, J. D. (2022). A systematic review on machine learning models for online learning and examination systems. PeerJ Computer Science, 8, e986. https://doi.org/10.7717/peerj-cs.986

Kim, S. (2023). Extracurricular Activities in Professional Education: An Integrative Review. BMC Medical Education, 23.

Kim, S., Jeong, H., Cho, H., Yu, J., & [others]. (2023). Extracurricular activities in medical education: An integrative literature review. BMC Medical Education, 23, Article 278. https://doi.org/10.1186/s12909-023-04245-w

Kumar, M., Singh, A., & Kaur, P. (2022). Machine learning-based student performance prediction and clustering for academic improvement. Education and Information Technologies, 27, 901–920. https://doi.org/10.1007/s10639-021-10708-2

LaForge-MacKenzie, K., Tombeau Cost, K., Tsujimoto, K. C., Crosbie, J., Charach, A., Anagnostou, E., Birken, C. S., Monga, S., Kelley, E., & Korczak, D. J. (2022). Participating in extracurricular activities and school sports during the COVID-19 pandemic: Associations with child and youth mental health. Frontiers in Sports and Active Living, 4, Article 936041. https://doi.org/10.3389/fspor.2022.936041

Liu, Y. (2022). Application of K-Means in Student Classification. Journal of Computer Applications in Education, 45(6), 1201–1210. https://doi.org/10.1007/s00521-022-06781-3

Lo, C. K. (2022). Numerical representation of student interests for predictive analytics in education. Journal of Learning Analytics, 9(2), 89–105.

Lo, K. (2022). [Selected Reference]. [Unknown Journal].

Namoun, A., & Alshanqiti, A. (2020). [Selected Reference]. [Unknown Journal].

Rizk, Y., Gad, W., & Hussein, R. (2021). Data-driven student performance prediction using clustering and classification approaches. Applied Sciences, 11(4), 1782. https://doi.org/10.3390/app11041782

Santos, F. (2022). Determining the optimal number of clusters using Elbow and Silhouette methods: A practical guide. Journal of Machine Learning Applications, 7(1), 45–58.

Santos, R. (2022). PCA-Enhanced K-Means for Student Behavioral and Extracurricular Profiling. International Journal of Educational Technology and Analytics, 6(2), 112–130.

Seo, J. (2022). [Selected Reference]. [Unknown Journal].

Vardakas, M., & Likas, A. (2024). [Selected Reference]. [Unknown Journal].

Wani, A. A. (2024). Comprehensive analysis of clustering algorithms: Exploring limitations and innovative solutions. PeerJ Computer Science. https://doi.org/10.7717/peerj-cs.2286

Zhang, Y., Yun, Y., An, R., Cui, J., Dai, H., & Shang, X. (2021). Educational data mining techniques for student performance prediction: Method review and comparison analysis. Frontiers in Psychology, 12, Article 698490. https://doi.org/10.3389/fpsyg.2021.698490