Predicting Smartphone Addiction Using Behavioral and Psychological Traits with Machine Learning

Smartphone addiction has become a growing concern, affecting mental health, academic performance, and social interactions. Existing prediction models often focus solely on behavioral data, such as screen time and app usage, or psychological traits, such as the Big Five personality dimensions. This study proposes an integrated machine learning approach that combines both behavioral and psychological factors to enhance the accuracy of smartphone addiction prediction among students.Using a dataset of 569 engineering students, the model incorporates variables such as screen time, app usage patterns, and personality traits, including neuroticism and conscientiousness. A Random Forest Classifier was employed due to its robustness and interpretability. The model achieved an overall accuracy of 96%, with precision, recall, and F1-scores of 0.94, 0.95, and 0.96, respectively, across different addiction levels. Feature importance analysis identified key behavioral and psychological predictors, while explainability techniques, such as Local Interpretable Model-agnostic Explanations (LIME), provided insights into individual predictions. These findings contribute to the development of a predictive framework for smartphone addiction, offering a practical tool for academic institutions and healthcare providers to implement targeted intervention strategies.