Comparative Analysis of Machine Learning Algorithms for Predicting Difficulty Disengaging from Social Media Among Students

Supardi; Djoko Soetarno; Rahmat Sulaiman; Chandra Kirana; Ari Amir Alkodri; Anisah

doi:10.63158/journalisi.v8i5.1735

Authors

Supardi Institut Sains dan Bisnis Atma Luhur
Djoko Soetarno Binus University
Rahmat Sulaiman Institut Sains dan Bisnis Atma Luhur
Chandra Kirana Institut Sains dan Bisnis Atma Luhur
Ari Amir Alkodri Institut Sains dan Bisnis Atma Luhur
Anisah Institut Sains dan Bisnis Atma Luhur

DOI:

https://doi.org/10.63158/journalisi.v8i5.1735

Keywords:

Social Media Disengagement Difficulty, Machine Learning, Behavioral Proxy Classification, Student Behavior, Digital Wellbeing

Abstract

Social media use can adversely affect students’ academic functioning and psychological well-being when disengagement becomes difficult. This study compared Random Forest (RF), XGBoost, and Support Vector Machine (SVM) for predicting self-reported difficulty disengaging from social media among university students. A cross-sectional survey dataset comprising 118 responses was analyzed, including 75 positive (63.6%) and 43 negative (36.4%) cases. The binary target represented a behavioral proxy rather than a clinically validated diagnosis of social media addiction. Using balanced class weighting and 10-fold stratified cross-validation, SVM achieved the highest mean accuracy (77.2%) and ROC-AUC (0.804), followed by RF (73.0%) and XGBoost (66.8%). However, the performance difference between SVM and RF was not statistically significant (Nadeau–Bengio corrected *p* = 0.102), while RF demonstrated greater resampling stability. The findings provide preliminary evidence for algorithm selection in behavioral proxy classification and support future digital well-being research. Interpretation is limited by the small, single-institution sample and single-item outcome measure; therefore, the results should not be used for clinical screening or institutional deployment without external validation using established psychometric instruments.

Downloads

Download data is not yet available.

References

[1] S. Kemp, “Digital 2024: Indonesia,” DataReportal, Feb. 2024. [Online]. Available: https://datareportal.com/reports/digital-2024-indonesia. Accessed: Aug. 1, 2024.

[2] S. Kemp, “Digital 2024: Global overview report,” DataReportal, Jan. 2024. [Online]. Available: https://datareportal.com/reports/digital-2024-global-overview-report. Accessed: Aug. 1, 2024.

[3] C. S. Andreassen and S. Pallesen, “Social network site addiction: An overview,” Curr. Pharm. Des., vol. 20, no. 25, pp. 4053–4061, 2014, doi: 10.2174/13816128113199990616.

[4] M. D. Griffiths, “A ‘components’ model of addiction within a biopsychosocial framework,” J. Subst. Use, vol. 10, no. 4, pp. 191–197, 2005, doi: 10.1080/14659890500114359.

[5] D. J. Kuss and M. D. Griffiths, “Social networking sites and addiction: Ten lessons learned,” Int. J. Environ. Res. Public Health, vol. 14, no. 3, Art. no. 311, 2017, doi: 10.3390/ijerph14030311.

[6] C. Marino, G. Gini, A. Vieno, and M. M. Spada, “The associations between problematic Facebook use, psychological distress and well-being among adolescents and young adults: A systematic review and meta-analysis,” J. Affect. Disord., vol. 226, pp. 274–281, 2019, doi: 10.1016/j.jad.2017.10.007.

[7] C. S. Andreassen, T. Torsheim, G. S. Brunborg, and S. Pallesen, “Development of a Facebook addiction scale,” Psychol. Rep., vol. 110, no. 2, pp. 501–517, 2012, doi: 10.2466/02.09.18.PR0.110.2.501-517.

[8] A. J. van Deursen, C. L. Bolle, S. M. Hegner, and P. A. M. Kommers, “Modeling habitual and addictive smartphone behavior: The role of smartphone usage types, emotional intelligence, social stress, self-regulation, age, and gender,” Comput. Hum. Behav., vol. 45, pp. 411–420, 2015, doi: 10.1016/j.chb.2014.12.039.

[9] F. Jiang et al., “Artificial intelligence in healthcare: Past, present and future,” Stroke Vasc. Neurol., vol. 2, no. 4, pp. 230–243, 2017, doi: 10.1136/svn-2017-000101.

[10] D. B. Dwyer, P. Falkai, and N. Koutsouleris, “Machine learning approaches for clinical psychology and psychiatry,” Annu. Rev. Clin. Psychol., vol. 14, pp. 91–118, 2018, doi: 10.1146/annurev-clinpsy-032816-045037.

[11] D. Loureiro and M. Veloso, “Machine learning for social media mental health classification: A systematic review,” IEEE Access, vol. 10, pp. 14125–14140, 2022, doi: 10.1109/ACCESS.2022.3147714.

[12] K. Siste et al., “The impact of physical distancing and associated factors towards internet addiction among adults in Indonesia during COVID-19 pandemic: A nationwide web-based study,” Front. Psychiatry, vol. 11, Art. no. 580977, 2020, doi: 10.3389/fpsyt.2020.580977.

[13] D. Lazer et al., “Computational social science,” Science, vol. 323, no. 5915, pp. 721–723, 2009, doi: 10.1126/science.1167742.

[14] G. Harman, N. Zain, and R. Mahadzir, “Social media addiction prediction using machine learning classifiers,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 5, pp. 478–487, 2021, doi: 10.14569/IJACSA.2021.0120555.

[15] N. Akhter and A. Nayab, “Predicting problematic social media use using ensemble machine learning,” Comput. Hum. Behav. Rep., vol. 6, Art. no. 100188, 2022, doi: 10.1016/j.chbr.2022.100188.

[16] C. S. Andreassen, S. Pallesen, and M. D. Griffiths, “The relationship between addictive use of social media, narcissism, and self-esteem: Findings from a large national survey,” Addict. Behav., vol. 64, pp. 287–293, 2017, doi: 10.1016/j.addbeh.2016.03.006.

[17] R. J. J. M. van den Eijnden, J. S. Lemmens, and P. M. Valkenburg, “The Social Media Disorder Scale,” Comput. Hum. Behav., vol. 61, pp. 478–487, 2016, doi: 10.1016/j.chb.2016.03.038.

[18] V. Agarwal, P. Mani, and S. Bodduluri, “Comparative performance of random forest and decision tree in health classification,” J. Med. Syst., vol. 46, no. 3, Art. no. 47, 2022, doi: 10.1007/s10916-022-01820-w.

[19] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., San Francisco, CA, USA, 2016, pp. 785–794, doi: 10.1145/2939672.2939785.

[20] H. Gao, L. Wang, and Y. Li, “Predicting internet addiction among university students using gradient boosting and random forest,” Comput. Educ.: Artif. Intell., vol. 3, Art. no. 100064, 2022, doi: 10.1016/j.caeai.2022.100064.

[21] A. B. R. Shatte, D. M. Hutchinson, and S. J. Teague, “Machine learning in mental health: A scoping review of methods and applications,” Psychol. Med., vol. 49, no. 9, pp. 1426–1448, 2019, doi: 10.1017/S0033291719000151.

[22] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.

[23] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995, doi: 10.1007/BF00994018.

[24] J. C. Nunnally and I. H. Bernstein, Psychometric Theory, 3rd ed. New York, NY, USA: McGraw-Hill, 1994.

[25] World Medical Association, “World Medical Association Declaration of Helsinki: Ethical principles for medical research involving human subjects,” JAMA, vol. 310, no. 20, pp. 2191–2194, 2013, doi: 10.1001/jama.2013.281053.