Model Klasifikasi Mental Siswa Menggunakan Algoritma Support Vector Machine
Abstract
Student mental health plays a vital role in academic performance and social well-being. This study aims to build a classification model using the Support Vector Machine (SVM) algorithm, based on 15 features covering demographic, academic, and behavioral aspects. The dataset, obtained from Kaggle, contains 426 records of junior and senior high school students. Key preprocessing steps include one-hot encoding, feature standardization, train-test splitting (80:20), and handling class imbalance with SMOTE. The model was trained using the Radial Basis Function (RBF) kernel and optimized using Grid Search CV to find the best parameters. Evaluation results show 65% accuracy, with better performance in predicting students without mental health issues (Absence). However, low recall for the Presence class indicates a need for improved strategies to handle data imbalance. This study highlights the potential of machine learning, particularly SVM, as a tool for early mental health detection in students, provided that effective data preprocessing is applied.
Keywords: Student mental health; classification; Support Vector Machine; SMOTE; machine learning
Abstrak
Kesehatan mental siswa berpengaruh besar terhadap prestasi akademik dan kesejahteraan sosial. Penelitian ini bertujuan membangun model klasifikasi kondisi mental siswa menggunakan algoritma Support Vector Machine (SVM) berbasis 15 fitur demografis, akademik, dan perilaku. Dataset yang digunakan berasal dari Kaggle, terdiri atas 426 data siswa SMP dan SMA. Tahapan penelitian meliputi preprocessing dengan one-hot encoding, standarisasi numerik, pembagian data (80:20), serta penanganan ketidakseimbangan data menggunakan SMOTE. Model dilatih menggunakan kernel Radial Basis Function (RBF) dan dioptimasi dengan Grid Search CV. Hasil evaluasi menunjukkan akurasi sebesar 65%, dengan kinerja lebih baik dalam mengenali siswa tanpa gangguan mental (absence) dibandingkan siswa dengan gangguan mental (presence). Rendahnya recall pada kelas Presence mengindikasikan perlunya strategi lanjutan terhadap ketidakseimbangan data. Penelitian ini menunjukkan bahwa machine learning, khususnya SVM, berpotensi sebagai alat bantu dalam deteksi awal kesehatan mental siswa jika disertai pengolahan data yang tepat.
Kata kunci: Kesehatan mental siswa; Klasifikasi; Support Vector Machine; SMOTE; Machine learning
References
B. Li and Y. Xu, “Research on evaluation model of College Students’ mental health,” in Proc. Int. Conf. Health Big Data Smart Sports (HBDSS), IEEE, Oct. 2021, pp. 114–117, doi: 10.1109/HBDSS54392.2021.00031.
N. Dhariwal et al., “A pilot study on AI-driven approaches for classification of mental health disorders,” Front. Hum. Neurosci., vol. 18, Apr. 2024, doi: 10.3389/fnhum.2024.1376338.
J. Chen, “Convolutional Neural Network with Fast Exponential Linear Unit Based Psychological Mental State Identification of College Students,” in Proc. 2nd Int. Conf. Networks, Multimedia and Inf. Technol. (NMITCON), IEEE, Aug. 2024, pp. 1–4, doi: 10.1109/NMITCON62075.2024.10699189.
M. Al-Farouni, J. Jeyasudha, V. N. Sree, R. Venkatasubramanian, and A. Ameelia Roseline, “Predictive Analytics for Mental Health Crises using Social Media Data with Attention Mechanism based Support Vector Machine Classification,” in Proc. 1st Int. Conf., Syst. and Inf. Technol. (SSITCON), IEEE, Oct. 2024, pp. 1–5, doi: 10.1109/SSITCON62437.2024.10796269.
R. Resmiati and T. Arifin, “Klasifikasi Pasien Kanker Payudara Menggunakan Metode Support Vector Machine dengan Backward Elimination,” SISTEMASI: J. Sist. Informasi, vol. 10, no. 2, pp. 381-392, May 2021, doi: 10.32520/stmsi.v10i2.1238.
A. Rahmatulloh, A. Taufiq, I. Darmawan, E. Haerani, and R. Rizal, “Support Vector Machine Parameters Optimization using Firefly Algorithm for Mental Health Prediction,” in Proc. 9th Int. Conf. Informatics Comput. (ICIC), IEEE, Oct. 2024, pp. 1–6, doi: 10.1109/ICIC64337.2024.10956409.
R. Ruliah, “Klasifikasi Stadium Trophozoite, Schizonts, Gametocyter pada Sediaan Darah Plasmodium Falciparum dengan Pendekatan Support Vector Machine,” Progresif: J. Ilm. Komput., vol. 6, no. 2, Aug. 2015, doi: http://dx.doi.org/10.35889/progresif.v6i2.78.
A. A. Shaikh, M. Al-Farouni, B. M. Manjula, S. Sivagami, and S. Devi, “Levy Flight Based Gannet Optimization Algorithm with Euclidean Distance-Support Vector Machine for Predictive Analysis of Mental Health Crisis Using Social Media Data,” in Proc. Int. Conf. Integrated Intell. Commun. Syst. (ICIICS), IEEE, Nov. 2024, pp. 1–5. doi: 10.1109/ICIICS63763.2024.10859744.
N. Alruwais, H. Alamro, M. M. Eltahir, A. S. Salama, M. Assiri, and N. A. Ahmed, “Modified arithmetic optimization algorithm with Deep Learning based data analytics for depression detection,” AIMS Math., vol. 8, no. 12, pp. 30335–30352, 2023, doi: 10.3934/math.20231549.
H. Hairani, K. Kurniawan, K. A. Latif, and M. Innuddin, “Metode Dempster-Shafer untuk Diagnosis Dini Jenis Penyakit Gangguan Jiwa Skizofrenia Berbasis Sistem Pakar,” SISTEMASI: J. Sist. Informasi, vol. 10, no. 2, pp. 280-290, May 2021, doi: 10.32520/stmsi.v10i2.1195.
A. W. Nugroho and N. Norhikmah, “Sentiment Analysis using the Support Vector Machine Algorithm on Covid_19,” SISTEMASI: J. Sist. Informasi, vol. 13, no. 4, p. 1758, Jul. 2024, doi: 10.32520/stmsi.v13i4.3778.
M. Nurkarifin, I. Hermanto, and M. G. Resmi, “Analisis Sentimen Terhadap Aplikasi Lowongan Kerja Menggunakan Lexicon Based Features Dan Support Vector Machine,” JUTISI: J. Ilm. Tek. Inform. dan Sist. Informasi, vol. 13, no. 1, Apr. 2024, doi: http://dx.doi.org/10.35889/jutisi.v13i1.
M. Husnah and R. Hidayat, “Analysis of Public Perception on Domestic Violence Cases using Support Vector Machine Algorithm,” SISTEMASI: J. Sist. Informasi, vol. 14, no. 1, pp. 117-126, Jan. 2025, doi: 10.32520/stmsi.v14i1.4724.
D. A. Pamungkas, A. Amali, and U. D. Soer, “Analisis Sentimen Publik Terhadap Polusi Udara di Kota Jakarta: Perbandingan Algoritma Support Vector Machine, Naive Bayes, dan Random Forest,” JUTISI: J. Ilm. Tek. Inform. dan Sist. Informasi, vol. 13, no. 3, pp. 132-145, Dec. 2025, doi: http://dx.doi.org/10.35889/jutisi.v13i3.2414.
M. Mulyana and W. Utomo, “Optimized Weight Evolutionary-based Support Vector Machine (SVM) Optimization for Comment Sentiment,” SISTEMASI: J. Sist. Informasi, vol. 14, no. 1, pp. 147-156, Jan. 2025, doi: 10.32520/stmsi.v14i1.4762.
How To Cite This :
Refbacks
- There are currently no refbacks.