International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1722174

1722174 Vol 10 · Issue 2 Download Paper

A Machine Learning Framework for Predicting Digital Wellness Risk: Gaming Addiction, Screen Time, Sleep, and Stress Among Students and Young Adults

Bhushan S. Ghodmare Mayur Jadhav Kumudini Zade Sairam Vaidya Yash Diware

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

How to cite this paper

Bhushan S. Ghodmare, Mayur Jadhav, Kumudini Zade, Sairam Vaidya, Yash Diware "A Machine Learning Framework for Predicting Digital Wellness Risk: Gaming Addiction, Screen Time, Sleep, and Stress Among Students and Young Adults" Iconic Research And Engineering Journals Volume 10 Issue 2 2026 Page 688-695 https://doi.org/10.64388/IREV10I2-1722174
Bhushan S. Ghodmare, Mayur Jadhav, Kumudini Zade, Sairam Vaidya, Yash Diware "A Machine Learning Framework for Predicting Digital Wellness Risk: Gaming Addiction, Screen Time, Sleep, and Stress Among Students and Young Adults" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026, doi: https://doi.org/10.64388/IREV10I2-1722174
Bhushan S. Ghodmare, Mayur Jadhav, Kumudini Zade, Sairam Vaidya, Yash Diware (2026). A Machine Learning Framework for Predicting Digital Wellness Risk: Gaming Addiction, Screen Time, Sleep, and Stress Among Students and Young Adults. Iconic Research And Engineering Journals, 10(2). doi: https://doi.org/10.64388/IREV10I2-1722174
Bhushan S. Ghodmare, Mayur Jadhav, Kumudini Zade, Sairam Vaidya, Yash Diware "A Machine Learning Framework for Predicting Digital Wellness Risk: Gaming Addiction, Screen Time, Sleep, and Stress Among Students and Young Adults" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026. Crossref, https://doi.org/10.64388/IREV10I2-1722174
@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}
  }