Modeling student satisfaction in online learning using random forest.

The rapid expansion of online education has intensified the need to investigate the multifactorial determinants of university students' satisfaction with digital learning platforms. While prior studies have often examined technical or pedagogical components in isolation, limited attention has been paid to their interaction with students' psychological well-being, particularly through nonlinear mechanisms. To address this gap, this study employs a Random Forest-based framework to model satisfaction using a multidimensional dataset from 782 university students. Measured variables included platform usability, content quality, emotional experience, and self-regulation. Data were standardized via Z-scores, and class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE). Model performance was evaluated using accuracy, F1-score, and area under the ROC curve (AUC). Results identified platform stability and content update frequency as the most influential predictors, with AUC values exceeding 0.95 across most satisfaction levels. Psychological factors-especially perceived enjoyment and emotional stability-also contributed significantly. Partial dependence plots revealed threshold and saturation effects, highlighting complex nonlinear patterns missed by traditional linear models. However, performance declined in predicting low-satisfaction cases (AUC = 0.70), likely due to subgroup underrepresentation. This study contributes theoretically by integrating cognitive-affective dimensions, methodologically by demonstrating the utility of machine learning in modeling nonlinear interactions, and practically by providing actionable insights for platform optimization. Future research should incorporate additional psychological constructs, such as cognitive load and resilience, and apply the model across more diverse learner populations to enhance generalizability and support inclusive, user-centered digital education.