Рақамли технологияларнинг назарий ва амалий масалалари Volume 8 Issue 4 (2025) · pp. 33-40
Modeling the Relationship Between Technology Use and Stress: a Data-Driven Behavioral Analysis
Туримов, Д., Сайдирасулов, Н., Киличев, Д.
Abstract
Understanding how daily behavioral patterns contribute to stress is increasingly important in a digitally saturated world. This study investigates the relationship between technology use, lifestyle behaviors, and stress levels using a data-driven machine learning framework. A gradient boosting regressor was trained on a behavioral dataset containing screen time, physical activity, sleep, and dietary patterns, excluding sensitive mental health indicators. The model achieved high predictive accuracy (R² = 0.979), significantly outperforming a baseline. Feature importance and SHAP analyses revealed that social media usage, work-related screen time, and low physical activity were the most impactful predictors of stress, while sleep quality and exercise were associated with lower stress levels. These results suggest that behavioral data alone can provide interpretable and reliable stress assessments, offering practical applications for digital wellness platforms and personalized feedback systems. The findings highlight the importance of monitoring digital habits as a non-clinical approach to mental well-being.
прогнозирование стрессаиспользование технологиймашинное обучениеэкранное времяповеденческие данныеSHAPанализ образа жизнимоделирование благополучиясоциальные сетифизическая активность
Metadata source: the journal's OAI-PMH archive · Sindex does not store the full text; it links to the source.