Prediksi Academic Burnout pada Mahasiswa: Analisis Komparatif Algoritma Support Vector Machine dan Random Forest: Prediction of Academic Burnout in College Students: A Comparative Analysis of Support Vector Machine and Random Forest Algorithms

Arbiansyah Adinegara; Suryarini Widodo

doi:10.57152/malcom.v5i4.2283

Authors

Arbiansyah Adinegara Universitas Gunadarma
Suryarini Widodo Universitas Gunadarma

DOI:

https://doi.org/10.57152/malcom.v5i4.2283

Keywords:

Academic Burnout, Machine Learning, Mahasiswa, Random Forest, Support Vector Machine

Abstract

Academic burnout telah menjadi masalah signifikan di kalangan mahasiswa, berdampak negatif pada kesehatan mental dan kinerja akademik. Penelitian ini bertujuan untuk melakukan analisis komparatif terhadap kinerja algoritma Support Vector Machine (SVM) dan Random Forest (RF) dalam memprediksi academic burnout pada mahasiswa di salah satu universitas di DKI Jakarta. Metode penelitian kuantitatif ini menggunakan data primer dari kuesioner Burnout Assessment Tool – Student Version (BAT-S) yang mencakup faktor pribadi, akademik, dan psikologis, serta data sekunder akademik mahasiswa. Data mentah kemudian melalui tahap persiapan yang meliputi pembersihan, penanganan outlier dengan teknik capping, standardisasi, dan penyeimbangan kelas menggunakan BorderlineSMOTE untuk mengatasi distribusi data yang tidak seimbang. Hasil pemodelan menunjukkan performa prediktif yang sangat tinggi untuk kedua algoritma setelah optimasi hyperparameter, dengan SVM mencapai akurasi 98,75% dan RF sebesar 97,50% pada data uji. Meskipun RF menunjukkan keunggulan pada metrik berbasis peringkat seperti ROC-AUC, SVM direkomendasikan sebagai model akhir karena memiliki profil risiko kesalahan yang lebih dapat diterima secara klinis, yakni tidak menghasilkan false negative yang berisiko tinggi. Penelitian ini membuktikan bahwa ML dapat menjadi alat efektif untuk deteksi dini risiko burnout, namun penelitian selanjutnya disarankan untuk mengeksplorasi algoritma yang lebih kompleks seperti gradient boosting dan melakukan analisis kepentingan fitur untuk pemahaman yang lebih mendalam.

Downloads

Download data is not yet available.

References

Z. Liu, Y. Xie, Z. Sun, D. Liu, H. Yin, and L. Shi, “Factors associated with academic burnout and its prevalence among university students: a cross-sectional study,” BMC Med. Educ., vol. 23, no. 1, Dec. 2023, doi: 10.1186/s12909-023-04316-y.

J. G. Greener, S. M. Kandathil, L. Moffat, and D. T. Jones, “A guide to machine learning for biologists,” Nat. Rev. Mol. Cell Biol., vol. 23, no. 1, pp. 40–55, 2022, doi: 10.1038/s41580-021-00407-0.

A. Frajerman, Y. Morvan, M. O. Krebs, P. Gorwood, and B. Chaumette, “Burnout in medical students before residency: A systematic review and meta-analysis,” European Psychiatry, vol. 55. Elsevier Masson SAS, pp. 36–42, Jan. 01, 2019, doi: 10.1016/j.eurpsy.2018.08.006.

J. Marôco et al., “Predictors of academic efficacy and dropout intention in university students: Can engagement suppress burnout?,” PLoS One, vol. 15, no. 10 October, Oct. 2020, doi: 10.1371/journal.pone.0239816.

M. Sheykhmousa, M. Mahdianpari, H. Ghanbari, F. Mohammadimanesh, P. Ghamisi, and S. Homayouni, “Support Vector Machine Versus Random Forest for Remote Sensing Image Classification: A Meta-Analysis and Systematic Review,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 13. Institute of Electrical and Electronics Engineers Inc., pp. 6308–6325, 2020, doi: 10.1109/JSTARS.2020.3026724.

S. Yu Hwanjoand Kim, “SVM Tutorial — Classification, Regression and Ranking,” in Handbook of Natural Computing, T. and K. J. N. Rozenberg Grzegorzand Bäck, Ed. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 479–506.

Y. Zhang, Y. Liu, and X. Yang, “Review of Support Vector Machine Theory and Application Research,” Int. Core J. Eng., 2021, doi: 10.6919/ICJE.202106_7(6).0049.

G. Biau and E. Scornet, “A random forest guided tour,” Test, vol. 25, no. 2, pp. 197–227, 2016, doi: 10.1007/s11749-016-0481-7.

J. Zhang, W. Yang, X. Luo, and L. Wang, “The Relationship Between Stress and Academic Burnout in CollegeStudents: Evidence from Longitudinal Data on Indirect Effects,” Front. Psychol., vol. 16, p. 1517920, 2025.

A. M. Shimaoka, R. C. Ferreira, and A. Goldman, “The evolution of CRISP-DM for Data Science: Methods, Processes and Frameworks,” SBC Rev. Comput. Sci., vol. 4, no. 1, pp. 28–43, 2024, doi: 10.5753/reviews.2024.3757.

Fraunhofer IST, “Implementation strategy for a data-mining project with CRISP-DM in surface technology,” 2025. .

M. Carmona-Halty, K. Alarcón-Castillo, C. Semir-González, G. Sepúlveda-Páez, and W. B. Schaufeli, “Burnout Assessment Tool for Students (BAT-S): evidence of validity in a Chilean sample of undergraduate university students,” Front. Psychol., vol. 15, 2024, doi: 10.3389/fpsyg.2024.1434412.

Muh Haritsah Hizbullah et al., “Analisis Psikometri Burnout Assessment Tool (BAT) For Student Versi Bahasa Indonesia,” J. Penelit. dan Pengukuran Psikol. JPPP, vol. 14, no. 1, pp. 30–38, Apr. 2025, doi: 10.21009/jppp.141.04.

I. Malashin, V. Tynchenko, A. Gantimurov, V. Nelyub, and A. Borodulin, “Support Vector Machines in Polymer Science: A Review,” Polymers, vol. 17, no. 4. Multidisciplinary Digital Publishing Institute (MDPI), Feb. 01, 2025, doi: 10.3390/polym17040491.

R. Ahuja and A. Banga, “Mental stress detection in university students using machine learning algorithms,” in Procedia Computer Science, 2019, vol. 152, pp. 349–353, doi: 10.1016/j.procs.2019.05.007.

R. Rois, M. Ray, A. Rahman, and S. K. Roy, “Prevalence and predicting factors of perceived stress among Bangladeshi university students using machine learning algorithms,” J. Heal. Popul. Nutr., vol. 40, no. 1, Dec. 2021, doi: 10.1186/s41043-021-00276-5.

L. R. Lara-González, M. A. Delgado-Luna, B. E. De León-Galván, and J. C. Venegas-Guerrero, “Comparison of Machine Learning algorithms for the Burnout projection,” ECORFAN Journal-Democratic Repub. Congo, pp. 1–8, Jun. 2021, doi: 10.35429/ejdrc.2021.12.7.1.8.

R. C. Chen, C. Dewi, S. W. Huang, and R. E. Caraka, “Selecting critical features for data classification based on machine learning methods,” J. Big Data, vol. 7, no. 1, Dec. 2020, doi: 10.1186/s40537-020-00327-4.

M. G. Pereira, M. Santos, R. Magalhães, C. Rodrigues, O. Araújo, and D. Durães, “Burnout Risk Profiles in Psychology Students: An Exploratory Study with Machine Learning,” Behav. Sci. (Basel)., vol. 15, no. 4, Apr. 2025, doi: 10.3390/bs15040505.

N. Nurdiansyah, F. S. Febriyan, Z. G. D. Amanta, D. A. Saputra, and W. M. Baihaqi, “Analisis Kesehatan Mental untuk Mencegah Gangguan Mental pada Mahasiswa Menggunakan Algoritma K-Nearest Neighbor (K-NN) dan Random Forest,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. 1, pp. 1–9, Nov. 2024, doi: 10.57152/malcom.v5i1.1537.

M. Grz?dzielewska, “Using Machine Learning in Burnout Prediction: A Survey,” Child and Adolescent Social Work Journal, vol. 38, no. 2. Springer, pp. 175–180, Apr. 01, 2021, doi: 10.1007/s10560-020-00733-w.

A. Villar and C. R. V. de Andrade, “Supervised machine learning algorithms for predicting student dropout and academic success: a comparative study,” Discov. Artif. Intell., vol. 4, no. 1, Dec. 2024, doi: 10.1007/s44163-023-00079-z.

N. S. Mohd Shafiee and S. Mutalib, “Prediction of Mental Health Problems among Higher Education Student Using Machine Learning,” Int. J. Educ. Manag. Eng., vol. 10, no. 6, pp. 1–9, Dec. 2020, doi: 10.5815/ijeme.2020.06.01.

P. A. Novianti, W. Yudiana, and S. Novita, “Can Learning Agility Predict Students’ Academic Burnout During Distance Learning,” J. Educ. Heal. Community Psychol., vol. 1, no. 1, p. 17, Apr. 2023, doi: 10.12928/jehcp.v1i1.25098.