KMAN Publication Inc. (KMANPUB) Journal of Assessment and Research in Applied Counseling (JARAC) 8 Serial Number 29 2026 04 01 Predicting Digital Burnout Using Machine Learning: The Role of Cognitive Flexibility, Emotional Regulation, Social Comparison, and Online Disinhibition Predicting Digital Burnout Using Machine Learning: The Role of Cognitive Flexibility, Emotional Regulation, Social Comparison, and Online Disinhibition 1 10 10.61838/kman.jarac.5243 EN Journal Article 2026 01 09 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> The present study aimed to predict digital burnout using machine learning techniques by examining the roles of cognitive flexibility, emotional regulation, social comparison, and online disinhibition.</p> <p><strong>Methods and Materials:</strong> This study employed a cross-sectional predictive design with a sample of 512 adult participants from the United States who were active daily users of digital technologies. Data were collected through standardized self-report instruments measuring digital burnout, cognitive flexibility, emotional regulation (reappraisal and suppression), social comparison, and online disinhibition. Data preprocessing included normalization, multiple imputation for missing values, and encoding of variables. Machine learning models, including Random Forest, Gradient Boosting, and Support Vector Machine, were implemented to predict digital burnout. Model performance was evaluated using 10-fold cross-validation with metrics such as root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R²). Feature importance was assessed using SHAP (Shapley Additive Explanations) values to determine the relative contribution of predictors.</p> <p><strong>Findings (inferentials only):</strong> The Gradient Boosting model demonstrated the highest predictive performance (R² = 0.68, RMSE = 0.38), outperforming Random Forest (R² = 0.62) and Support Vector Machine (R² = 0.55). Social comparison emerged as the strongest positive predictor of digital burnout (importance = 0.31), followed by online disinhibition (0.26). Cognitive flexibility (β = negative contribution; importance = 0.18) and emotional regulation via reappraisal (importance = 0.14) were significant protective factors, whereas emotional suppression showed a smaller positive effect (0.11). All predictors were statistically significant (p &lt; .01), and the model demonstrated high stability across cross-validation folds (R² range = 0.66–0.71).</p> <p><strong>Conclusion:</strong> Digital burnout is a multifactorial phenomenon best predicted through integrative machine learning models, with social comparison and online disinhibition as primary risk factors and cognitive flexibility and adaptive emotional regulation as key protective mechanisms.</p> </td> </tr> </tbody> </table> https://journals.kmanpub.com/index.php/jarac/article/download/5243/9520