PREDICTING STUDENT STRESS AND MENTAL HEALTH USING SUPPORT VECTOR MACHINE

Miftahul Farida; Panji Bintoro; Ferly Ardhy; Agus Wantoro; Dwi Yana Ayu Andini

doi:10.33365/jtst.v7i1.1030

Miftahul Farida Informatics Engineering, Faculty of Technology and Informatics, Aisyah University, Indonesia
Panji Bintoro Software Engineering, Faculty of Technology and Informatics, Aisyah University, Indonesia
Ferly Ardhy Informatics Engineering, Faculty of Technology and Informatics, Aisyah University, Indonesia
Agus Wantoro Informatics Engineering, Faculty of Technology and Informatics, Aisyah University, Indonesia
Dwi Yana Ayu Andini Software Engineering, Faculty of Technology and Informatics, Aisyah University, Indonesia

DOI: https://doi.org/10.33365/jtst.v7i1.1030

Keywords: klasifikasi stres, kesehatan mental, support vector machine, survei likert, machine learning

Abstract

Student mental health is a critical issue in Indonesia, with more than 30% of students experiencing symptoms of stress and depression due to academic, social, and economic pressures. This study aims to develop a stress classification pipeline based on a Likert-scale survey using the Support Vector Machine (SVM) algorithm. A quantitative cross-sectional method was employed with 293 active university student respondents, encompassing stages of data preprocessing, labeling based on median scores, normalization, feature selection, model training, and evaluation. The evaluation results show an accuracy of 89.77%, with precision, recall, and F1-score values consistently ranging between 0.897–0.898. The confusion matrix indicates a balanced classification distribution between the “Stress” and “No Stress” classes. The discussion reveals that dominant factors in stress classification include academic pressure, sleep disturbance, and social support, aligning with established psychological stress theories. This study demonstrates that the SVM model is effective in classifying student stress and that the constructed pipeline adheres to the principles of reproducibility, auditability, and data ethics. The proposed system has the potential to be developed into a practical and responsible stress monitoring tool accessible to educational institutions.

References

[1] A. Hapsari, A. S. Nursuwanda, H. Zuhriyah, and D. J. Vresdian, “Klasifikasi Kesehatan Mental Mahasiswa Model TMAS dengan Algoritma Decision Tree, Logistic Regression, dan Random Forest,” INTEK J. Inform. dan Teknol. Inf., vol. 7, no. 2, pp. 55–64, 2024, doi: 10.37729/intek.v7i2.5690.
[2] M. Razavi et al., “Machine Learning, Deep Learning, and Data Preprocessing Techniques for Detecting, Predicting, and Monitoring Stress and Stress-Related Mental Disorders: Scoping Review,” JMIR Ment. Heal., vol. 11, pp. 1–28, 2024, doi: 10.2196/53714.
[3] S. Ghosh et al., “Predicting Stress among Students via Psychometric Assessments and Machine Learning,” ACM Int. Conf. Proceeding Ser., no. May, pp. 662–669, 2024, doi: 10.1145/3652037.3663949.
[4] U. Madububambachu, A. Ukpebor, and U. Ihezue, “Machine Learning Techniques to Predict Mental Health Diagnoses: A Systematic Literature Review,” Clin. Pract. Epidemiol. Ment. Heal., vol. 20, no. 1, pp. 1–16, 2024, doi: 10.2174/0117450179315688240607052117.
[5] M. Kang, S. Shin, G. Zhang, J. Jung, and Y. T. Kim, “Mental stress classification based on a support vector machine and naive bayes using electrocardiogram signals,” Sensors, vol. 21, no. 23, 2021, doi: 10.3390/s21237916.
[6] A. Singh, K. Singh, A. Kumar, A. Shrivastava, and S. Kumar, “Machine Learning Algorithms for Detecting Mental Stress in College Students,” 2024 IEEE 9th Int. Conf. Converg. Technol. I2CT 2024, 2024, doi: 10.1109/I2CT61223.2024.10544243.
[7] S. B. Harahap and Y. Yamasari, “Klasifikasi Tingkat Stres Mahasiswa Menggunakan RMSProp untuk Arsitektur Artificial Neural Network,” J. Informatics Comput. Sci., vol. 5, no. 04, pp. 560–567, 2024, doi: 10.26740/jinacs.v5n04.p560-567.
[8] L. Susanti, “Klasifikasi Tingkat Stress pada Mahasiswa Teknik Informatika dalam Melakukan Perkuliahan Metode Hybrid Menggunakan Algoritma Naive Bayes,” STRING (Satuan Tulisan Ris. dan Inov. Teknol., vol. 8, no. 3, p. 243, 2024, doi: 10.30998/string.v8i3.17096.
[9] M. Fadhilla, R. Wandri, A. Hanafiah, P. R. Setiawan, Y. Arta, and S. Daulay, “Analisis Performa Algoritma Machine Learning Untuk Identifikasi Depresi Pada Mahasiswa,” J. Informatics Manag. Inf. Technol., vol. 5, no. 1, pp. 40–47, 2025, doi: 10.47065/jimat.v5i1.473.
[10] M. F. Alamsyah and A. Wijaya, “Perbandingan Metode KNN dan Naïve Bayes dalam Deteksi Tingkat Stres Berdasarkan Ekspresi Wajah,” J. Inform. J. Pengemb. IT, vol. 10, no. 2, pp. 359–369, 2025, doi: 10.30591/jpit.v10i2.8513.
[11] S. D. Amalia, M. A. Barata, and P. E. Yuwita, “Optimization of Random Forest Algorithm with Backward Elimination Method in Classification of Academic Stress Levels,” J. Appl. Informatics Comput., vol. 9, no. 3, pp. 633–641, 2025, doi: 10.30871/jaic.v9i3.9280.
[12] V. Oktaviani, N. Rosmawarni, and M. P. Muslim, “Perbandingan Kinerja Random Forest Dan Smote Random Forest Dalam Mendeteksi Dan Mengukur Tingkat Stres Pada Mahasiswa Tingkat Akhir,” Inform. J. Ilmu Komput., vol. 20, no. 1, pp. 43–49, 2024, doi: 10.52958/iftk.v20i1.9158.