Bapak Prediksi Depresi Mahasiswa Menggunakan Algoritma Random Forest Berbasis Data Psikososial Depression Prediction Among University Students Using a Random Forest Algorithm Based on Psychosocial Data : Prediksi Depresi Mahasiswa: Pendekatan Berbasis Data Psikososial Menggunakan Algoritma Random Forest

Abiyya Alfahrizi Putra Arifiansyah Abiyya; Muhammad Afandi; Dodi Dwi Riskianto; Sudriyanto Sudriyanto

doi:10.30787/restia.v4i1.2100

Penulis

Abiyya Alfahrizi Putra Arifiansyah Abiyya Universitas Nurul Jadid
Muhammad Afandi Universitas Nurul Jadid, Probolinggo
Dodi Dwi Riskianto Universitas Nurul Jadid, Probolinggo
Sudriyanto Universitas Nurul Jadid, Probolinggo

DOI:

https://doi.org/10.30787/restia.v4i1.2100

Kata Kunci:

Student Depression, Machine Learning, Prediction, Random Forest

Abstrak

Depresi pada mahasiswa merupakan isu psikologis yang kian meningkat dan berdampak pada performa akademik serta kesejahteraan mental. Penelitian ini bertujuan membangun model prediksi depresi berbasis data psikososial dengan algoritma Random Forest. Dataset diperoleh dari sumber terbuka dan mencakup variabel demografi, kebiasaan, dan kondisi emosional mahasiswa. Proses prapemrosesan dilakukan dengan pembersihan data, konversi kategorikal ke numerik, dan penyeimbangan kelas. Hasil evaluasi menunjukkan model mencapai akurasi 87,0% dan f1-score 86,7%, menandakan performa yang andal dalam mengidentifikasi potensi depresi. Temuan ini berkontribusi dalam upaya deteksi dini depresi mahasiswa di lingkungan pendidikan tinggi.

Referensi

G. Limenih, A. MacDougall, M. Wedlake, and E. Nouvet, “Depression and global mental health in the global south: a critical analysis of policy and discourse,” Int. J. Soc. Determ. Heal. Heal. Serv., vol. 54, no. 2, pp. 95–107, 2024.

K. S. Chaudhari, M. P. Dhapkas, A. Kumar, and R. G. Ingle, “Mental disorders–a serious global concern that needs to address,” Int J Pharm Qual Assur, vol. 15, no. 02, pp. 973–978, 2024.

G. I. Al Jowf et al., “A public health perspective of post-traumatic stress disorder,” Int. J. Environ. Res. Public Health, vol. 19, no. 11, p. 6474, 2022.

N. R. Rohmah and M. Mahrus, “Mengidentifikasi Faktor-faktor Penyebab Stres Akademik pada Mahasiswa dan Strategi Pengelolaannya,” JIEM J. Islam. Educ. Manag., vol. 5, no. 1, pp. 36–43, 2024.

V. Blanco, M. Salmerón, P. Otero, and F. L. Vázquez, “Symptoms of Depression, Anxiety, and Stress and Prevalence of Major Depression and Its Predictors in Female University Students.,” Int. J. Environ. Res. Public Health, vol. 18, no. 11, May 2021, doi: 10.3390/ijerph18115845.

S. Verma, C. Sharma, G. Aggarwal, and P. Upadhya, “Artificial intelligence-based approach for classification and prediction of mental health,” in 2024 14th International Conference on Cloud Computing, Data Science & Engineering (Confluence), IEEE, 2024, pp. 708–713.

B. Acharya, “Comparative analysis of machine learning algorithms: KNN, SVM, decision tree and logistic regression for efficiency and performance,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 12, no. 11, pp. 614–619, 2024.

L. F. Voges, L. C. Jarren, and S. Seifert, “Exploitation of surrogate variables in random forests for unbiased analysis of mutual impact and importance of features,” Bioinformatics, vol. 39, no. 8, p. btad471, 2023.

J. Buesa et al., “Predictors of postpartum depression in threatened preterm labour: importance of psychosocial factors,” Spanish J. Psychiatry Ment. Heal., vol. 17, no. 1, pp. 51–54, 2024.

H. S. BALTACI, D. Kucuker, I. Ozkilic, U. Y. Karatas, and H. A. Ozdemir, “Investigation of Variables Predicting Depression in College Students.,” Eurasian J. Educ. Res., no. 93, 2021.

W. Narkbunnum and K. Wisaeng, “Prediction of Depression for Undergraduate Students Based on Imbalanced Data by Using Data Mining Techniques,” Appl. Syst. Innov., vol. 5, no. 6, p. 120, 2022.

G. S. Dhillon and S. Kaur, “Depression Among College Students: Prevalence And Associated Risk Factors,” Indian J. Ment. Heal., vol. 9, no. 2, 2022.

N. Kosaraju, S. R. Sankepally, and K. Mallikharjuna Rao, “Categorical data: Need, encoding, selection of encoding method and its emergence in machine learning models—a practical review study on heart disease prediction dataset using pearson correlation,” in Proceedings of International Conference on Data Science and Applications: ICDSA 2022, Volume 1, Springer, 2023, pp. 369–382.

A. Bansal, A. Verma, S. Singh, and Y. Jain, “Combination of oversampling and undersampling techniques on imbalanced datasets,” in International Conference on Innovative Computing and Communications: Proceedings of ICICC 2022, Volume 3, Springer, 2022, pp. 647–656.

M. Maindola et al., “Utilizing random forests for high-accuracy classification in medical diagnostics,” in 2024 7th International Conference on Contemporary Computing and Informatics (IC3I), IEEE, 2024, pp. 1679–1685.

K. Vita, P. Yana, B. Liliia, and V. Dmytro, “AUTOMATED DETECTION OF POTENTIALLY DANGEROUS URL ADDRESSES USING THE SCIKIT-LEARN LIBRARY,” pp. 353–357, 2024.

F. Aziz, S. Abasa, and A. Andyka, “Pengembangan dan Validasi Model Hybrid Machine Learning untuk Diagnosis Awal Depresi,” J. Pharm. Appl. Comput. Sci., vol. 3, no. 1, pp. 8–15, 2025.

O. Iparraguirre-Villanueva, C. Paulino-Moreno, A. Epifanía-Huerta, and C. Torres-Ceclén, “Machine Learning Models to Classify and Predict Depression in College Students.,” Int. J. Interact. Mob. Technol., vol. 18, no. 14, 2024.