Klasifikasi Tingkat Kecanduan Media Sosial dengan Menggunakan Algoritma Random Forest
DOI:
https://doi.org/10.29407/7996m579Keywords:
Klasifikasi, Mahasiswa, Media Sosial, Random ForestAbstract
Penelitian ini membahas Klasifikasi Tingkat Kecanduan Media Sosial dengan Menggunakan Algoritma Random Forest. Topik ini penting karena penggunaan media sosial yang berlebihan dapat memengaruhi konsentrasi, kesehatan mental, kualitas tidur, dan performa akademik. Data penelitian diambil dari dataset publik yang memuat variabel perilaku seperti durasi penggunaan harian, frekuensi akses, distraksi, kecemasan, perubahan mood, dan dampak akademik. Setelah melalui tahap pra-pemrosesan, termasuk pemilihan fitur, pembersihan data, dan pembagian data, model Random Forest dilatih untuk mengklasifikasikan tiga kategori kecanduan, yaitu rendah, sedang, dan tinggi. Evaluasi dilakukan menggunakan akurasi, precision, recall, F1-score, dan confusion matrix. Model mencapai akurasi 87,94% dengan performa sangat baik pada kelas rendah dan tinggi, sedangkan kelas sedang masih menunjukkan tumpang tindih perilaku. Hasil penelitian menunjukkan bahwa Random Forest mampu mengenali pola kecanduan digital dengan cukup stabil, dan sistem yang dikembangkan menghasilkan rekomendasi otomatis sesuai tingkat kecanduan sehingga dapat membantu mahasiswa memahami kondisi mereka dan mengambil langkah mitigasi. Temuan ini menegaskan bahwa pendekatan machine learning dapat diterapkan secara efektif untuk mendeteksi dan memetakan kecanduan media sosial.
Downloads
References
[1] L. Zhao, “The impact of social media use types and social media addiction on subjective well-being of college students: A comparative analysis of addicted and non-addicted students,” Computers in Human Behavior Reports, vol. 4, p. 100122, 2021, doi: https://doi.org/10.1016/j.chbr.2021.100122.
[2] O. Tyrväinen, H. Pirkkalainen, M. Salo, and H. Karjaluoto, “Overloaded yet addicted? A meta-analysis of the outcomes of social media overload,” Telematics and Informatics, vol. 98, p. 102247, 2025, doi: https://doi.org/10.1016/j.tele.2025.102247.
[3] Z. Peng, X. Su, and Y. Hou, “How do GenAI and social media provide psychosocial information support for cancer survivors and professionals? An analysis using structural topic modeling for exploration and comparison,” European Journal of Oncology Nursing, vol. 79, p. 103018, 2025, doi: https://doi.org/10.1016/j.ejon.2025.103018.
[4] D. Bagus Reknadi, M. Ghofar Rohman, and A. Fraga Listyo Utomo, “Adaptation of Contrastive Learning and Augmentation for Indonesian Product Review Classification on Unbalanced Data Using Deep Learning and NLP.”
[5] T. C. Marshall, “Social media observation of ex-partners is associated with greater breakup distress, negative affect, and jealousy,” Comput Human Behav, vol. 176, p. 108869, 2026, doi: https://doi.org/10.1016/j.chb.2025.108869.
[6] D. R. Galos and J. Frese, “Online social class cues and employability: Experimental evidence from Germany,” Soc Sci Res, vol. 133, p. 103258, 2026, doi: https://doi.org/10.1016/j.ssresearch.2025.103258.
[7] C. Chen and L. Leung, “Are you addicted to Candy Crush Saga? An exploratory study linking psychological factors to mobile social game addiction,” Telematics and Informatics, vol. 33, no. 4, pp. 1155–1166, 2016, doi: https://doi.org/10.1016/j.tele.2015.11.005.
[8] H. Kupermintz, E. K. Tesler, H. Gleit, and D. Kopelman-Rubin, “Measuring Adults’ Social and Emotional Competencies: Development and Validation of a New Self-report Questionnaire – Social and Emotional Competencies Questionnaire - Hebrew (SECQ-H),” Social and Emotional Learning: Research, Practice, and Policy, p. 100168, 2025, doi: https://doi.org/10.1016/j.sel.2025.100168.
[9] L. Boltanski, “The social uses of the body,” Soc Sci Med, vol. 385, p. 118141, 2025, doi: https://doi.org/10.1016/j.socscimed.2025.118141.
[10] Y. Qu, C. Yu, C. Li, and Y. Yang, “Laser-Printed Document Classification Using Random Forest and Grey Prediction Models,” iScience, p. 114131, 2025, doi: https://doi.org/10.1016/j.isci.2025.114131.
[11] H. Hara, Y. Fujita, and K. Tsuda, “Population estimation by random forest analysis using Social Sensors,” Procedia Comput Sci, vol. 176, pp. 1893–1902, 2020, doi: https://doi.org/10.1016/j.procs.2020.09.229.
[12] V. A. Fitri, R. Andreswari, and M. A. Hasibuan, “Sentiment Analysis of Social Media Twitter with Case of Anti-LGBT Campaign in Indonesia using Naïve Bayes, Decision Tree, and Random Forest Algorithm,” Procedia Comput Sci, vol. 161, pp. 765–772, 2019, doi: https://doi.org/10.1016/j.procs.2019.11.181.
[13] M. Kamal, Md. Al Amin, M. Ahmed, P. Ahmed, and Md. A. Islam, “Mathematical modeling and optimal control of social media addiction with stability and sensitivity analysis,” Franklin Open, vol. 12, p. 100354, 2025, doi: https://doi.org/10.1016/j.fraope.2025.100354.
[14] D. Jitoku et al., “Psychophysiological respone of individuals with internet gaming disorder to gaming content from social media,” Addictive Behaviors Reports, vol. 22, p. 100641, 2025, doi: https://doi.org/10.1016/j.abrep.2025.100641.
[15] F. Z. Allahverdi, N. Bayer, and M. Kart, “Perceived social media addiction explained through perceived organizational support, burnout subscales, and the number of years on the job,” Acta Psychol (Amst), vol. 255, p. 104976, 2025, doi: https://doi.org/10.1016/j.actpsy.2025.104976.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Wahyu Setyanto, David Yoga Wicaksono
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
