Home / Current Issue / Paper 1722174
A Machine Learning Framework for Predicting Digital Wellness Risk: Gaming Addiction, Screen Time, Sleep, and Stress Among Students and Young Adults
Subject area: Science,Engineering and Technology · Area of research: Digital Health / eHealth
DOI: https://doi.org/10.64388/IREV10I2-1722174
Abstract
Excessive smartphone use, online gaming, and social media engagement among students and young adults have been linked to poor sleep, elevated stress, reduced academic performance, and, in severe cases, clinically recognized gaming disorder. Existing digital-wellness tools remain limited to single-metric screen-time counters and rarely combine multiple behavioral dimensions into one predictive framework. This paper presents a machine learning framework that integrates seven behavioral indicators — daily screen time, gaming duration, sleep duration, stress level, physical activity, academic performance, and social interaction — into a single multi-class digital-wellness risk classifier. Five supervised algorithms (Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Gradient Boosting) are trained and compared on a literature-calibrated pilot dataset of 600 records. Logistic Regression achieves the best performance, with 85.0% accuracy, an F1-score of 0.850, and a weighted ROC-AUC of 0.934, followed closely by Gradient Boosting and Random Forest. Feature-importance analysis confirms screen time and gaming duration as the dominant predictors, consistent with prior behavioral research. The framework is proposed as a non-clinical, tier-based screening and recommendation aid for educational institutions, pending validation on real survey data.
Keywords
Digital Health, Digital Wellness, Gaming Addiction, Machine Learning, Screen Time, Sleep Quality, Stress Prediction, Student Mental Health
References
[1] American Psychiatric Association, Diagnostic and Statistical Manual of Mental Disorders, 5th ed. Arlington, VA: American Psychiatric Publishing, 2013.
[2] World Health Organization, “6C51 Gaming disorder,” International Classification of Diseases, 11th Revision (ICD-11), 2019. [Online]. Available: https://icd.who.int/browse/2025-01/mms/en
[3] M. Zhao and W. Hao, “Challenges of gaming disorder: Suggestions from a public health perspective,” General Psychiatry, vol. 32, no. 3, p. e100086, 2019.
[4] M. E. Cecchinato, J. Rooksby, A. Hiniker, S. A. Munson, K. Lukoff, L. Ciolfi, A. Thieme, and D. Harrison, “Designing for digital wellbeing: A research & practice agenda,” in Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems (CHI EA ’19), 2019, pp. 1–8.
[5] 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,” Preventive Medicine Reports, vol. 12, pp. 271–283, 2018.
[6] L. Exelmans and J. Van den Bulck, “Bedtime mobile phone use and sleep in adults,” Social Science & Medicine, vol. 148, pp. 93–101, 2016.
[7] A. Rajkomar et al., “Scalable and accurate deep learning with electronic health records,” npj Digital Medicine, vol. 1, no. 18, pp. 1–10, 2018.
[8] L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
[9] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, 1995.
[10] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD ’16), 2016, pp. 785–794.
[11] J. R. Quinlan, “Induction of decision trees,” Machine Learning, vol. 1, no. 1, pp. 81–106, 1986.
[12] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
How to cite this paper
@article{1722174,
author = {Bhushan S. Ghodmare, Mayur Jadhav, Kumudini Zade, Sairam Vaidya, Yash Diware},
title = {A Machine Learning Framework for Predicting Digital Wellness Risk: Gaming Addiction, Screen Time, Sleep, and Stress Among Students and Young Adults},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {2},
pages = {688-695},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1722174.pdf},
abstract = {Excessive smartphone use, online gaming, and social media engagement among students and young adults have been linked to poor sleep, elevated stress, reduced academic performance, and, in severe cases, clinically recognized gaming disorder. Existing digital-wellness tools remain limited to single-metric screen-time counters and rarely combine multiple behavioral dimensions into one predictive framework. This paper presents a machine learning framework that integrates seven behavioral indicators — daily screen time, gaming duration, sleep duration, stress level, physical activity, academic performance, and social interaction — into a single multi-class digital-wellness risk classifier. Five supervised algorithms (Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Gradient Boosting) are trained and compared on a literature-calibrated pilot dataset of 600 records. Logistic Regression achieves the best performance, with 85.0% accuracy, an F1-score of 0.850, and a weighted ROC-AUC of 0.934, followed closely by Gradient Boosting and Random Forest. Feature-importance analysis confirms screen time and gaming duration as the dominant predictors, consistent with prior behavioral research. The framework is proposed as a non-clinical, tier-based screening and recommendation aid for educational institutions, pending validation on real survey data.},
keywords = {Digital Health, Digital Wellness, Gaming Addiction, Machine Learning, Screen Time, Sleep Quality, Stress Prediction, Student Mental Health},
month = {August},
doi = {https://doi.org/10.64388/IREV10I2-1722174}
}