Comparison of SVM, Random Forest, and Logistic Regression Performance n Student Mental Health Screening
Article Sidebar
Main Article Content
Abstract
Mental health is an essential aspect for university students, as undetected mental health disorders can have a significant impact on students' academic performance and well-being. This study contributes by evaluating Synthetic Minority Oversampling Technique (SMOTE)'s role in improving classification models' performance. Despite the increasing use of machine learning in mental health detection, limited research has addressed the challenges posed by imbalanced datasets, particularly in smaller student populations. This research aims to develop a mental health early detection system based on student data from Multi Data University Palembang using the Mental Health Scale (SKM)-12 mental health measurement. The system aims to remind students' awareness of the importance of mental health. To improve accuracy, this research compares the performance of three models, namely Support Vector Machine, Random Forest, and Logistic Regression, both with and without using SMOTE. The dataset obtained is 78 students, and SKM-12 consists of several groups, namely optimal mental health profile with symbol (+-), maximum mental illness profile with symbol (++), minimum mental illness profile with symbol (--), and minimal mental health profile with symbol (-+). The results of this study using the Logistic Regression method using SMOTE obtained better model performance compared to other methods, with an accuracy of 89.28%, an average class precision of 89.5%, an average class recall of 89.75%, and an average F1 - class score of 88.5%. This research shows that overcoming class imbalance using SMOTE can significantly improve the performance of mental health classification models.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
I. A. Ridlo, (2020), “Pandemi COVID-19 dan Tantangan Kebijakan Kesehatan Mental di Indonesia,” INSAN Jurnal Psikologi dan Kesehatan Mental, vol. 5, no. 2, pp. 155–164, doi:10.20473/jpkm.v5i12020.155-164. DOI: https://doi.org/10.20473/jpkm.V5I22020.162-171
Z. Zulkarnain and S. Fatimah, (2019), “Kesehatan dan Mental dan Kebahagiaan: Tinjauan Psikologi Islam,” Mawa’Izh: Jurnal Dakwah Dan Pengembangan Sosial Kemanusiaan, vol. 10, no. 1, pp. 18–38, doi:10.32923/maw.v10i1.715. DOI: https://doi.org/10.32923/maw.v10i1.715
Y. Huang, S. Li, B. Lin, S. Ma, J. Guo, and C. Wang, (2022), “Early Detection of College Students’ Psychological Problems Based on Decision Tree Model,” Frontiers in Psychology, vol. 13, pp. 1–10, doi:10.3389/fpsyg.2022.946998. DOI: https://doi.org/10.3389/fpsyg.2022.946998
A. H. Azizah, S. Warsini, and K. P. Yuliandari, (2023), “Hubungan Stres Akademik dengan Kecenderungan Depresi Mahasiswa Ilmu Keperawatan Universitas Gadjah Mada pada Masa Transisi Pandemi COVID-19,” Jurnal Keperawatan Klinis dan Komunitas (Clinical and Community Nursing Journal), vol. 7, no. 2, p. 114, doi:10.22146/jkkk.84827. DOI: https://doi.org/10.22146/jkkk.84827
M. K. Sari and E. A. Susmiatin, (2023), “Deteksi Dini Kesehatan Mental Emosional pada Mahasiswa,” Jurnal Ilmiah STIKES Yarsi Mataram, vol. 13, no. 1, pp. 10–17, doi:10.57267/jisym.v13i1.226. DOI: https://doi.org/10.57267/jisym.v13i1.226
M. Rijal, F. Aziz, and S. Abasa, (2024), “Prediksi Depresi : Inovasi Terkini Dalam Kesehatan Mental Melalui Metode Machine Learning Depression Prediction : Recent Innovations in Mental Health Journal Pharmacy and Application,” Journal Pharmacy and Application of Computer Sciences, vol. 2, no. 1, pp. 9–14. DOI: https://doi.org/10.59823/jopacs.v2i1.47
H. D. Putra, L. Khairani, and D. Hastari, (2023), “Perbandingan Algoritma Naive Bayes Classifier dan Support Vector Machine untuk Klasifikasi Data Kesehatan Mental Mahasiswa,” in SENTIMAS: Seminar Nasional Penelitian dan Pengabdian Masyarakat, pp. 120–125.
S. Mutalib, N. S. M. Shafiee, and S. Abdul-Rahman, (2021), “Mental Health Prediction Models Using Machine Learning in Higher Education Institution,” Turkish Journal of Computer and Mathematics Education (TURCOMAT), vol. 12, no. 5, pp. 1782–1792, doi:10.17762/turcomat.v12i5.2181. DOI: https://doi.org/10.17762/turcomat.v12i5.2181
G. Ryan, P. Katarina, and D. Suhartono, (2023), “MBTI Personality Prediction Using Machine Learning and SMOTE for Balancing Data Based on Statement Sentences,” Information (Switzerland), vol. 14, no. 4, doi:10.3390/info14040217. DOI: https://doi.org/10.3390/info14040217
F. M. Basysyar, G. Dwilestari, and A. I. Purnamasari, (2024), “Analysis Student Emotions And Mental Health on Cumulative GPA Using Machine Learning and Smote,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 10, no. 2, pp. 361–368, doi:10.33480/jitk.v10i2.5967.ANALYSIS. DOI: https://doi.org/10.33480/jitk.v10i2.5967
R. Aziz, R. Mangestuti, Y. Sholichatun, I. T. Rahayu, E. K. Purwaningtyas, and E. N. Wahyuni, (2022), “Model Pengukuran Kesehatan Mental pada Mahasiswa di Perguruan Tinggi Islam,” Journal of Islamic and Contemporary Psychology (JICOP), vol. 1, no. 2, pp. 83–94, doi:10.25299/jicop.v1i2.8251. DOI: https://doi.org/10.25299/jicop.v1i2.8251
C. T. Veit and J. E. Ware, (1983), “The structure of psychological distress and well-being in general populations,” Journal of Consulting and Clinical Psychology, vol. 51, no. 5, pp. 730–742, doi:10.1037/0022-006X.51.5.730. DOI: https://doi.org/10.1037//0022-006X.51.5.730
R. Aziz, (2015), “Aplikasi Model RASCH dalam Pengujian Alat Ukur Kesehatan Mental di Tempat Kerja,” Psikoislamika : Jurnal Psikologi dan Psikologi Islam, vol. 12, no. 2, p. 29, doi:10.18860/psi.v12i2.6402. DOI: https://doi.org/10.18860/psi.v12i2.6402
R. Aziz and Zamroni, (2020), “Analisis Faktor Konfirmatori Terhadap Alat Ukur Kesehatan Mental Berdasarkan Teori Dual Model,” Psikoislamika : Jurnal Psikologi dan Psikologi Islam, vol. 16, no. 2, p. 1, doi:10.18860/psi.v16i2.8199. DOI: https://doi.org/10.18860/psi.v16i2.8199
V. Wijaya, M. Fadli, Y. A. Dharma, and M. R. Pribadi, (2022), “Pengembangan UI/UX pada aplikasi Go-Print Dengan menggunakan metode design thinking,” MDP Student Conference (MSC), vol. 1, no. 1, pp. 298–305.
D. I. Pushpita Anna Octaviani, Yuciana Wilandari, (2014), “Penerapan Metode SVM Pada Data Akreditasi Sekolah Dasar Di Kabupaten Magelang,” Jurnal Gaussian, vol. 3, no. 8, pp. 811–820.
M. Athoillah, M. I. Irawan, and M. Imah, (2015), “Support Vector Machine Untuk Image Retrieval,” Seminar Nasional Matematika dan Pendidikan Matematika, no. 978, pp. 279–287.
R. R. Fiska, (2017), “Penerapan Teknik Data Mining dengan Metode Support Vector Machine (SVM) untuk Memprediksi Siswa yang Berpeluang Drop Out (Studi Kasus di SMKN 1 Sutera),” Sains dan Teknologi Informasi (SATIN), vol. 3, no. 1, pp. 15–23. DOI: https://doi.org/10.33372/stn.v3i1.200
F. Akbar and Rahmaddeni, (2022), “Komparasi Algoritma Machine Learning untuk Memprediksi Penyakit Alzheimer,” Jurnal Komputer Terapan, vol. 8, no. 2, pp. 236–245. DOI: https://doi.org/10.35143/jkt.v8i2.5713
N. K. Dewi, S. Y. Mulyadi, and U. D. Syafitri, (2012), “Penerapan Metode Random Forest Dalam Driver Analysis,” Forum Statistika Dan Komputasi, vol. 16, no. 1, pp. 35–43.
G. A. M. Ashfania, T. Prahasto, A. Widodo, and T. Warsokusumo, (2023), “Penggunaan Algoritma Random Forest untuk Klasifikasi berbasis Kinerja Efisiensi Energi pada Sistem Pembangkit Daya,” Rotasi, vol. 24, no. 3, pp. 14–21.
S. A. Assaidi and F. Amin, (2022), “Analisis Sentimen Evaluasi Pembelajaran Tatap Muka 100 Persen pada Pengguna Twitter menggunakan Metode Logistic Regression,” Jurnal Pendidikan Tambusai, vol. 6, no. 2, pp. 13217–13227, doi:doi.org/10.31004/jptam.v6i2.4543.
Y. Tampil, H. Komaliq, and Y. Langi, (2017), “Analisis Regresi Logistik Untuk Menentukan Faktor-Faktor Yang Mempengaruhi Indeks Prestasi Kumulatif (IPK) Mahasiswa FMIPA Universitas Sam Ratulangi Manado,” d’CARTESIAN, vol. 6, no. 2, p. 56, doi:10.35799/dc.6.2.2017.17023. DOI: https://doi.org/10.35799/dc.6.2.2017.17023
A. Maulvi Inayat, (2021), “Analisis Sentimen Berdasarkan Aspek Menggunakan Elman Recurrent Neural Network,” Thesis, Universitas Komputer Indonesia., pp. 9–30.
R. Siringoringo, (2018), “Klasifikasi Data Tidak Seimbang Menggunakan Algoritma SMOTE dan K-Nearest Neighbor,” Jurnal ISD, vol. 3, no. 1, pp. 44–49.
M. Fadli, V. Wijaya, M. R. Pribadi, and W. Widhiarso, (2023), “Effect of TF-IDF Extraction and Application of SMOTE on Model Performance in Detecting Spam Email,” in International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), pp. 637–641. DOI: https://doi.org/10.1109/EECSI59885.2023.10295851
R. Ridwan, E. H. Hermaliani, and M. Ernawati, (2024), “Penerapan: Penerapan Metode SMOTE Untuk Mengatasi Imbalanced Data Pada Klasifikasi Ujaran Kebencian,” Computer Science (CO-SCIENCE), vol. 4, no. 1, pp. 80–88. DOI: https://doi.org/10.31294/coscience.v4i1.2990
A. N. Kasanah, M. Muladi, and U. Pujianto, (2019), “Penerapan Teknik SMOTE untuk Mengatasi Imbalance Class dalam Klasifikasi Objektivitas Berita Online Menggunakan Algoritma KNN,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 3, no. 2, pp. 196–201, doi:https://doi.org/10.29207/resti.v3i2.945. DOI: https://doi.org/10.29207/resti.v3i2.945