KMAN Publication Inc. (KMANPUB) Journal of Adolescent and Youth Psychological Studies (JAYPS) 2981-2526 7 Serial Number 44 2026 04 10 Predicting Problematic Internet Use via Impulsivity, Emotion Dysregulation, Reward-System Reactivity, and Loneliness Using SVM Models Predicting Problematic Internet Use via Impulsivity, Emotion Dysregulation, Reward-System Reactivity, and Loneliness Using SVM Models 1 10 10.61838/kman.jayps.5259 EN Journal Article 2025 10 21 <table> <tbody> <tr> <td> <p><strong>Objective:</strong> The present study aimed to predict the severity of problematic internet use by examining the complex interplay of impulsivity, emotion dysregulation, reward-system reactivity, and loneliness utilizing advanced Support Vector Machine (SVM) models.</p> <p><strong>Methods and Materials: </strong>A cross-sectional predictive design was employed, collecting self-reported data from a sample of Argentine adults using validated psychometric questionnaires to measure problematic internet use, impulsivity, emotion dysregulation, reward-system reactivity, and subjective loneliness. Data analysis involved preliminary bivariate correlations and the application of machine learning classification algorithms, specifically training and evaluating various SVM kernels to distinguish between high and low-to-moderate problematic internet users. Finally, permutation feature importance techniques were utilized to rank the predictive weight of the psychological constructs within the optimal model.</p> <p><strong>Findings: </strong>Preliminary bivariate analyses revealed significant positive correlations between problematic internet use and all predictor variables, most notably emotion dysregulation ( ) and impulsivity ( ). The Radial Basis Function (RBF) kernel emerged as the optimal SVM model, demonstrating robust predictive capability with an overall classification accuracy of and an F1-score of . Furthermore, permutation feature importance analysis identified emotion dysregulation as the most critical predictor of pathological digital behavior, followed sequentially by impulsivity, loneliness, and reward-system reactivity.</p> <p><strong>Conclusion: </strong>Problematic internet use is profoundly driven by underlying deficits in emotional and behavioral self-regulation, underscoring the necessity for targeted psychological interventions that address these core vulnerabilities rather than merely restricting screen time.</p> </td> </tr> </tbody> </table> https://journals.kmanpub.com/index.php/jayps/article/download/5259/9555