Klasifikasi Tiga Tingkat Stres Mahasiswa dari Pola Aktivitas Harian dengan Support Vector Machine Kernel Radial Basis Function
DOI:
https://doi.org/10.56427/jcbd.v5i3.1101
Keywords:
Tingkat Stres, Support Vector Machine, Klasifikasi, Pola Aktivitas Harian, Kernel RBFAbstract
Tingkat stres mahasiswa dapat berkaitan dengan pola aktivitas harian dan karakteristik akademik. Penelitian ini bertujuan mengevaluasi kemampuan Support Vector Machine (SVM) dengan kernel Radial Basis Function (RBF) dalam mengklasifikasikan tingkat stres mahasiswa ke dalam kategori Low, Moderate, dan High. Data penelitian berupa 2.000 observasi dari dataset sekunder Study Habits and Activities of Students yang diperoleh dari Kaggle, dengan enam variabel prediktor, yaitu jam belajar, kegiatan ekstrakurikuler, durasi tidur, interaksi sosial, aktivitas fisik, dan IPK. Tahap pre-processing meliputi pemeriksaan data, normalisasi Min-Max, ordinal encoding pada label, dan pembagian data secara stratified dengan rasio 80:20. Model dibangun menggunakan kernel RBF dengan C = 1,0, γ = scale, dan strategi One-vs-One. Pengujian pada 400 data uji menghasilkan akurasi 96,50% serta macro average precision 97,17%, recall 95,21%, dan F1-score 96,13%. Analisis korelasi Pearson menunjukkan bahwa jam belajar (r = 0,7388) dan IPK (r = 0,5504) berkorelasi positif dengan tingkat stres, sedangkan durasi tidur dan aktivitas fisik berkorelasi negatif lemah. Hasil ini menunjukkan performa klasifikasi yang tinggi pada pembagian data yang digunakan, tetapi masih terbatas karena evaluasi belum mencakup cross-validation, perbandingan algoritma, dan validasi eksternal. Tingkat stres dalam penelitian ini tidak digunakan sebagai ukuran langsung academic burnout.
Downloads
References
[1] M. Gardani, D. R. R. Bradford, K. Russell, S. Allan, L. Beattie, J. G. Ellis, and U. Akram, “A systematic review and meta-analysis of poor sleep, insomnia symptoms and stress in undergraduate students,” Sleep Med. Rev., vol. 61, Art. no. 101565, 2022, doi: 10.1016/j.smrv.2021.101565.
[2] K. Chen, F. Liu, L. Mou, P. Zhao, and L. Guo, “How physical exercise impacts academic burnout in college students: The mediating effects of self-efficacy and resilience,” Front. Psychol., vol. 13, Art. no. 964169, 2022, doi: 10.3389/fpsyg.2022.964169.
[3] X. Wang, M. Yang, L. Ren, Q. Wang, S. Liang, Y. Li, Y. Li, Q. Zhan, S. Huang, K. Xie, J. Liu, X. Li, and S. Wu, “Burnout and depression in college students,” Psychiatry Res., vol. 335, Art. no. 115828, 2024, doi: 10.1016/j.psychres.2024.115828.
[4] M. Megawati, M. Widyaningsih, A. Hadi, and E. A. Safithry, “Sistem klasifikasi tingkat stres mahasiswa tingkat akhir berbasis web menggunakan Support Vector Machine,” J. Sains dan Inform., vol. 12, no. 1, pp. 21–30, 2026, doi: 10.34128/jsi.v12i1.1877.
[5] R. de Filippis and A. Al Foysal, “Comprehensive analysis of stress factors affecting students: A machine learning approach,” Discov. Artif. Intell., vol. 4, no. 1, Art. no. 62, 2024, doi: 10.1007/s44163-024-00169-6.
[6] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995, doi: 10.1007/BF00994018.
[7] A. S. A. Afnan, “Study habits and activities of students,” Kaggle, 2025. [Online]. Available: https://www.kaggle.com/datasets/afnansaifafnan/study-habits-and-activities-of-students
[8] Q. Hu and W. B. Schaufeli, “The factorial validity of the Maslach Burnout Inventory–Student Survey in China,” Psychol. Rep., vol. 105, no. 2, pp. 394–408, 2009, doi: 10.2466/pr0.105.2.394-408.
[9] I. Portoghese, M. P. Leiter, C. Maslach, M. Galletta, F. Porru, E. D’Aloja, G. Finco, and M. Campagna, “Measuring burnout among university students: Factorial validity, invariance, and latent profiles of the Italian version of the Maslach Burnout Inventory Student Survey (MBI-SS),” Front. Psychol., vol. 9, Art. no. 2105, 2018, doi: 10.3389/fpsyg.2018.02105.
[10] D. H. Rahman, “Validasi School Burnout Inventory versi Bahasa Indonesia,” J. Penelit. Ilmu Pendidik., vol. 13, no. 2, pp. 85–93, 2020, doi: 10.21831/jpipfip.v13i2.32579.
[11] E. López-Gómez, R. González-Fernández, and B. Khampirat, “Psychometric study of the Maslach Burnout Inventory-Student Survey on Thai university students,” Sci. Rep., vol. 15, no. 1, Art. no. 1802, 2025, doi: 10.1038/s41598-024-84829-8.
[12] B. Schölkopf and A. J. Smola, Learning with kernels: Support vector machines, regularization, optimization, and beyond. Cambridge, MA, USA: MIT Press, 2002.
[13] W. Pirie, “Spearman rank correlation: Introduction,” in Wiley StatsRef: Statistics Reference Online. Hoboken, NJ, USA: Wiley, 2014, doi: 10.1002/9781118445112.stat02773.
[14] P. Schober, C. Boer, and L. A. Schwarte, “Correlation coefficients: Appropriate use and interpretation,” Anesth. Analg., vol. 126, no. 5, pp. 1763–1768, 2018, doi: 10.1213/ANE.0000000000002864.
[15] M. Suardiaz-Muro, M. Morante-Ruiz, M. Ortega-Moreno, M. A. Ruiz, P. Martín-Plasencia, and A. Vela-Bueno, “Sleep and academic performance in university students: A systematic review,” Rev. Neurol., vol. 71, no. 2, pp. 43–53, 2020, doi: 10.33588/rn.7102.2020015.
[16] D. J. Madigan, L. E. Kim, and H. L. Glandorf, “Interventions to reduce burnout in students: A systematic review and meta-analysis,” Eur. J. Psychol. Educ., vol. 39, no. 2, pp. 931–957, 2024, doi: 10.1007/s10212-023-00731-3.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Faruqi, Mhd. Ikhsan Rifki

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.







