Prediksi Risiko Kesehatan Mental Mahasiswa Menggunakan Klasifikasi Naive Bayes

Abstract

The mental health of university students is a growing concern as academic, emotional, and social pressures contribute to increased psychological risks. This study aims to classify mental health risk levels Low, Medium, and High among students using the Naïve Bayes classification algorithm. A dataset consisting of 1,000 entries and 11 key variables was utilized, covering academic, psychological, and behavioral factors. The preprocessing stage included data cleaning, label encoding, normalization, and rule-based labeling to determine the target classes. Model training and testing were conducted using stratified data splitting to preserve class distribution. The initial model achieved a classification accuracy of 88,67%, with macro average F1-score of 0.87 and weighted average F1-score of 0.88. Grid Search optimization with k-fold cross-validation was applied but showed no significant improvement, indicating the model was already in optimal configuration. Furthermore, probabilistic analysis revealed that Sleep Quality and Study Stress Level were the most influential features in predicting mental health risks. The findings suggest that Naïve Bayes is effective for multi-class classification with interpretable results. This research contributes to early detection efforts and offers a foundation for targeted interventions in university mental health management.