Analisis Kecenderungan Depresi Remaja dalam Penggunaan Media Sosial dengan Algoritma Random Forest
DOI:
https://doi.org/10.35889/progresif.v22i3.3257Keywords:
Random Forest, Regresi, DepresiAbstract
Depression is a major factor in Bali’s high suicide rates, particularly among social media-active adolescents. This study analyzes the effects of social media usage intensity, addiction, and sleep quality on adolescents’ mental health using the Random Forest algorithm. Quantitative research involved data exploration, preprocessing, modeling, hyperparameter tuning, and evaluation with R² and MSE. From 36 valid respondents, the Addicted Score was the strongest predictor of sleep quality and mental health (feature importance ±0.7), exceeding average daily usage (0.2–0.3). Negative correlations linked addiction to mental health (r = –0.6257) and sleep quality (r = –0.4588). Models achieved R² of 0.19 (sleep quality) and 0.38 (mental health). Findings show addictive behavior impacts more than usage duration, so prevention should focus on controlling social media addiction.
Keywords: Random Forest; Regression; Depression
Abstrak
Depresi merupakan salah satu faktor utama yang berkontribusi terhadap tingginya angka bunuh diri di Bali, terutama pada remaja yang aktif menggunakan media sosial. Penelitian ini bertujuan menganalisis pengaruh intensitas penggunaan media sosial, kecanduan media sosial, dan kualitas tidur terhadap kesehatan mental remaja menggunakan algoritma Random Forest. Penelitian kuantitatif dilakukan melalui tahapan eksplorasi data, preprocessing, pemodelan, hyperparameter tuning, dan evaluasi menggunakan R² serta MSE. Berdasarkan 36 data responden valid, Addicted Score menjadi faktor paling dominan dalam memprediksi kualitas tidur dan kesehatan mental (feature importance ±0,7), dibandingkan rata-rata penggunaan media sosial harian (0,2–0,3). Korelasi menunjukkan hubungan negatif antara kecanduan media sosial dengan kesehatan mental (r = –0,6257) dan kualitas tidur (r = –0,4588). Model menghasilkan R² 0,19 untuk kualitas tidur dan 0,38 untuk kesehatan mental. Temuan menunjukkan bahwa perilaku adiktif lebih berpengaruh daripada durasi penggunaan, sehingga pencegahan perlu menekankan pengendalian kecanduan media sosial.
References
[1] S. Onie et al., “Indonesia’s first suicide statistics profile: an analysis of suicide and attempt rates, underreporting, geographic distribution, gender, method, and rurality,” The Lancet Regional Health - Southeast Asia, vol. 22, p. 100368, 2024, doi: https://doi.org/10.1016/j.lansea.2024.100368.
[2] J. K. N. Chan et al., “All-cause and cause-specific mortality in people with depression: a large-scale systematic review and meta-analysis of relative risk and aggravating or attenuating factors, including antidepressant treatment,” World Psychiatry, vol. 24, no. 3, pp. 404–421, Oct. 2025, doi: https://doi.org/10.1002/wps.21354.
[3] World Health Organization, “Depressive disorder (depression),” 2025. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/depression
[4] The Lancet Psychiatry, “Global Burden of Disease 2021: mental health messages,” Lancet Psychiatry, vol. 11, no. 8, p. 573, 2024, doi: https://doi.org/10.1016/S2215-0366(24)00222-0.
[5] J. A. Naslund, A. Bondre, J. Torous, and K. A. Aschbrenner, “Social Media and Mental Health: Benefits, Risks, and Opportunities for Research and Practice,” J. Technol. Behav. Sci., vol. 5, no. 3, pp. 245–257, 2020, doi: 10.1007/s41347-020-00134-x.
[6] Asosiasi Penyelenggara Jasa Internet Indonesia (APJII), “Survei Penetrasi dan Perilaku Pengguna Internet Indonesia 2023,” 2023.
[7] Reva Diena Mustaqina and Sri Mulyeni, “Dampak Penggunaan Media Sosial terhadap Gangguan Psikologis Mahasiswa,” RISOMA : Jurnal Riset Sosial Humaniora dan Pendidikan, vol. 4, no. 2, pp. 09–20, Mar. 2026, doi: 10.62383/risoma.v4i2.1521.
[8] F. Kaligis et al., “The mediating role of social media disorder in the relationship between social media use and self-harm behavior in Indonesian adolescents,” Front. Public Health, vol. Volume 13-2025, 2025, doi: 10.3389/fpubh.2025.1663729.
[9] D. Safitri and Sujarwo, “Eksplorasi Dampak Penggunaan Media Sosial terhadap Kesehatan Mental Remaja,” Triwikrama: Jurnal Ilmu Sosial, vol. 9, no. 11, pp. 201–211, 2025, doi: 10.9963/6awwk344.
[10] R. Jones, I. Reppa, and P. Reed, “Social media dependency, depression and self-esteem for Cymraeg and English-speaking adolescents,” Behaviour & Information Technology, vol. 0, no. 0, pp. 1–14, 2025, doi: 10.1080/0144929X.2025.2455395.
[11] B. Han and C. Myers, “Perceptions of overuse, underuse, and change of use of a social media site: definition, measurement instrument, and their managerial impacts,” Behaviour & Information Technology, vol. 37, no. 3, pp. 247–257, 2018, doi: 10.1080/0144929X.2018.1432687.
[12] G. Brandenberg, P. Ozimek, H.-W. Bierhoff, and C. Janker, “The relation between use intensity of private and professional SNS, social comparison, self-esteem, and depressive tendencies in the light of self-regulation,” Behaviour & Information Technology, vol. 38, no. 6, pp. 578–591, 2019, doi: 10.1080/0144929X.2018.1545049.
[13] Y.-K. Lee, C.-T. Chang, Y. Lin, and Z.-H. Cheng, “The dark side of smartphone usage: Psychological traits, compulsive behavior and technostress,” Comput. Human Behav., vol. 31, pp. 373–383, 2014, doi: https://doi.org/10.1016/j.chb.2013.10.047.
[14] K. Saha, J. Torous, E. D. Caine, and M. De Choudhury, “Psychosocial Effects of the COVID-19 Pandemic: Large-scale Quasi-Experimental Study on Social Media,” J Med Internet Res, vol. 22, no. 11, p. e22600, 2020, doi: 10.2196/22600.
[15] J. C. Eichstaedt et al., “Facebook language predicts depression in medical records,” Proceedings of the National Academy of Sciences, vol. 115, no. 44, pp. 11203–11208, 2018, doi: 10.1073/pnas.1802331115.
[16] C. Qi, “A double-edged sword? Exploring the impact of students’ academic usage of mobile devices on technostress and academic performance,” Behaviour & Information Technology, vol. 38, no. 12, pp. 1337–1354, 2019, doi: 10.1080/0144929X.2019.1585476.
[17] J. M. Twenge and W. K. Campbell, “Associations between screen time and lower psychological well-being among children and adolescents: Evidence from a population-based study,” Prev. Med. Rep., vol. 12, pp. 271–283, 2018, doi: https://doi.org/10.1016/j.pmedr.2018.10.003.
[18] M. Walker, Why We Sleep: Unlocking the Power of Sleep and Dreams. New York: Scribner, 2017.
[19] D. J. Yu, Y. K. Wing, T. M. H. Li, and N. Y. Chan, “The Impact of Social Media Use on Sleep and Mental Health in Youth: a Scoping Review.,” Curr. Psychiatry Rep., vol. 26, no. 3, pp. 104–119, 2024, doi: 10.1007/s11920-024-01481-9.
[20] J. Wang, N. Wang, P. Liu, and Y. Liu, “Social network site addiction, sleep quality, depression and adolescent difficulty describing feelings: a moderated mediation model,” BMC Psychol., vol. 13, no. 1, p. 57, 2025, doi: 10.1186/s40359-025-02372-1.
[21] S. Han, B. Williamson, and Y. Fong, “Improving random forest predictions in small datasets from two-phase sampling designs,” BMC Med. Inform. Decis. Mak., vol. 21, Sep. 2021, doi: 10.1186/s12911-021-01688-3.
[22] N. Novianti, S. Alkadri, and I. Fakhruzi, “Klasifikasi Penyakit Hipertensi Menggunakan Metode Random Forest,” Progresif: Jurnal Ilmiah Komputer, vol. 20, no. 1, pp. 380–392, 2024, [Online]. Available: https://ojs.stmik-banjarbaru.ac.id/index.php/progresif/article/view/1663
[23] Y. Liu, Y. Pan, F. Wang, W. Li, L. Gao, and G. Zhao, “Multivariate machine learning regression approaches to predict adolescent suicide risk,” Psychiatry Res., vol. 361, p. 117160, 2026, doi: https://doi.org/10.1016/j.psychres.2026.117160.
[24] C. Yu, X. Kong, W. Yu, X. Ni, J. Chen, and X. Liao, “Machine learning models for predicting the risk of depressive symptoms in Chinese college students,” Front. Psychiatry, vol. Volume 16-2025, 2025, doi: 10.3389/fpsyt.2025.1648585.
[25] D. A. Fife and J. D’Onofrio, “Common, uncommon, and novel applications of random forest in psychological research,” Behav. Res. Methods, vol. 55, no. 5, pp. 2447–2466, 2023, doi: 10.3758/s13428-022-01901-9.
[26] E. J. Kim, S. K. Kim, S. H. Jung, and Y. S. Ryu, “Predictive factors of adolescents’ happiness: a random forest analysis of the 2023 Korea Youth Risk Behavior Survey,” Child Health Nurs Res, vol. 31, no. 2, pp. 85–95, Apr. 2025, doi: 10.4094/chnr.2024.049.
[27] O. Ahmed, E. I. Walsh, A. Dawel, K. Alateeq, D. A. Espinoza Oyarce, and N. Cherbuin, “Social media use, mental health and sleep: A systematic review with meta-analyses,” J. Affect. Disord., vol. 367, pp. 701–712, 2024, doi: https://doi.org/10.1016/j.jad.2024.08.193.
[28] W. Chalermchutidej, B. Manaboriboon, G. Sanpawitayakul, S. Theppiban, and S. In-iw, “Sleep, social media use and mental health in female adolescents aged 12 to 18 years old during the COVID-19 pandemic,” BMC Pediatr., vol. 23, no. 1, p. 398, 2023, doi: 10.1186/s12887-023-04218-4.
