PERBANDINGAN KINERJA ALGORITMA MACHINE LEARNING DALAM MEMPREDIKSI TINGKAT STRES MAHASISWA BERDASARKAN FAKTOR AKADEMIK DAN NON-AKADEMIK
DOI:
https://doi.org/10.54314/jssr.v9i1.5805Abstract
Abstract: Stress among students is a growing phenomenon due to high academic demands, changes in the social environment, and various non-academic pressures faced during their studies. Stress that is not managed properly can have a negative impact on students' mental health, motivation to study, and academic achievement. Therefore, an approach is needed that can identify and predict students' stress levels objectively and based on data. This study aims to analyze and compare the performance of several machine learning algorithms in predicting student stress levels based on academic and non-academic factors. The dataset used in this study is Student Stress Factors, which includes various variables such as Sleep Quality, Academic Achievement, Study Load, Frequency of Headaches, Extracurricular Activities, Level of Social Support, Screen Time, etc. The algorithms applied are Support Vector Machine and Naive Bayes. This research is expected to contribute to the development of a decision support system for early detection of student stress levels, as well as serve as a reference for educational institutions in designing strategies for the prevention and management of mental health issues in higher education environments. Keywords: Machine Learning, Support Vector Machine, Naive Bayes, Stress, Student Abstrak: Stres pada mahasiswa merupakan fenomena yang semakin meningkat seiring dengan tuntutan akademik yang tinggi, perubahan lingkungan sosial, serta berbagai tekanan non-akademik yang dihadapi selama masa studi. Kondisi stres yang tidak dikelola dengan baik dapat berdampak negatif terhadap kesehatan mental, motivasi belajar, serta capaian akademik mahasiswa. Oleh karena itu, diperlukan suatu pendekatan yang mampu mengidentifikasi dan memprediksi tingkat stres mahasiswa secara objektif dan berbasis data. Penelitian ini bertujuan untuk menganalisis serta membandingkan kinerja algoritma machine learning dalam memprediksi tingkat stres mahasiswa berdasarkan faktor akademik dan non-akademik. Dataset yang digunakan pada penelitian ini adalah Student Stress Factors, yang mencakup berbagai variabel seperti Kualitas Tidur, Prestasi Akademik, Beban Studi, Frekuensi Sakit Kepala, Kegiatan Ekstrakurikuler, Tingkat Dukungan Sosial, Jam Waktu Layar, dll. Algoritma yang diterapkan yaitu Support Vector Machine dan Naive Bayes dengan akurasi tertinggi dihasilkan oleh Algoritma SVM dengan akurasi 85% sedangkan NV memiliki akurasi 83%. Penelitian ini diharapkan dapat memberikan kontribusi dalam pengembangan sistem pendukung keputusan untuk deteksi dini tingkat stres mahasiswa, serta menjadi referensi bagi institusi pendidikan dalam merancang strategi pencegahan dan penanganan masalah kesehatan mental di lingkungan perguruan tinggi. Kata kunci: Machine Learning, Support Vector Machine, Naive Bayes, Stres, MahasiswaDownloads
References
AFISTIAN, R., BETIE, F., & WAHYU, E. S. (2025). HUBUNGAN ADAPTASI DIRI DENGAN TINGKAT STRES MAHASISWA BARU FAKULTAS ILMU KEPERAWATAN UNIVERSITAS ISLAM SULTAN AGUNG SEMARANG. CORONA: JURNAL ILMU KESEHATAN UMUM, PSIKOLOG, KEPERAWATAN DAN KEBIDANAN Учредители: Asosiasi Riset Ilmu Manajemen dan Bisnis Indonesia, 3(1), 243-252.
Wistarini, N. N. I. P., & Marheni, A. (2019). Peran dukungan sosial keluarga dan efikasi diri terhadap stres akademik mahasiswa baru Fakultas Kedokteran Universitas Udayana angkatan 2018. Jurnal Psikologi Udayana Edisi Khusus Psikologi Pendidikan, 4(3), 164-173.
Parraga-alava, J. (2024). Stress Detection among Higher Education Students : A Comprehensive Systematic Review of Machine Learning Approaches. 2024 Tenth International Conference on EDemocracy & EGovernment (ICEDEG), 1–8. https://doi.org/10.1109/ICEDEG61611.2024.10702055.
Dhinora, M. Y., & Mailoa, E. (2025). Analisa Tweet Mahasiswa untuk Deteksi Gejala Depresi dengan Penerapan Natural Language Processing. Jurnal Indonesia: Manajemen Informatika dan Komunikasi, 6(2), 1193-1211.
Luci, M., Hernandez, Z., Daza, A., Dario, R., Rivera, M., Gustavo, E., Alamo, S., & Apaza-perez, G. (2025). Comparative Analysis of Machine Learning Algorithms for Academic Performance Prediction Using Oversampling Techniques. 12(3), 227–245. https://doi.org/10.33168/JLISS.2025.
Tan, J., Mao, Y., & Li, Y. (2024). The Application of Big Data Technology in Teaching College Students’ Mental Health Education in Colleges and Universities. Applied Mathematics and Nonlinear Sciences, 9(1), 1–17.
Sasane, S., & Mulla, Z. A. S. (2024). Predictive Modelling Of Stress Levels: A Comparative Analysis Of Machine Learning Algorithms. Journal of Advanced Zoology, 45(S-4), 153–158.
Adie Wahyudi Oktavia Gama, Agustini Degni Melsy Grren, I Gusti Ngurah Darma Paramartha, G., & Humaswara Prathama, Ni Made Widnyani, M. W. P. D. (2025). PENERAPAN ALGORITMA NAÃVE BAYES UNTUK PREDIKSI PENYAKIT DEPRESI PADA MAHASISWA. Journal of Language and Health, 6(2), 199–216.
Chowdhury, S., Chowdury, A. F., Islam, A., & Bary, A. N. (2024). Machine Learning and Deep Learning Models for Predicting Mental Health Disorders and Performance Analysis through Chatbot Interactions. 12(9), 38–60.
Amin, M., Efendi, S., & Elveny, M. (2024, October). Analysis of Machine Learning Methods for Solving Cumulative Vehicle Routing Problem. In 2024 Ninth International Conference on Informatics and Computing (ICIC) (pp. 1-4). IEEE.
Novelan, M. S., & Iqbal, M. (2025, November). Comparative Analysis of the Performance of K-Nearest Neighbor (K-NN) and Naive Bayes Algorithms on User Satisfaction Levels of the Tokopedia Application. In Proceedings of The International Conference on Computer Science, Engineering, Social Science, and Multi-Disciplinary Studies (Vol. 1, pp. 218-224).
Fatah, Z., & Hasanah, U. (2025). Prediksi Tingkat Stress dan Kesehatan Mental Mahasiswa Menggunakan Algoritma SVM. 4, 200–207.
Sharma, N. (2023). Analysis o f Student ’ s Academic Performance based on their Time Spent on Extra-Curricular Activities using Machine Learning Techniques. 15(1), 46–57. https://doi.org/10.5815/ijmecs.2023.01.04.
Thanh Noi, P., & Kappas, M. (2018). Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery. Sensors, 18(1), 18. https://doi.org/10.3390/s18010018.
Kartianom, K., Arpandi, A., K. Kassymova, G., & Ndayizeye, O. (2022). Prediction model of teacher candidate student graduation status: Decision Tree C4.5, Naive Bayes, and k-NN. Ekspose: Jurnal Penelitian Hukum Dan Pendidikan, 21(2), 1419–1427. https://doi.org/10.30863/ekspose.v21i2.3407
