<![CDATA[Anxiety disorders are one of the psychological problems commonly experienced by students, which can affect their quality of life and academic performance. Early detection of this disorder is crucial for providing appropriate intervention. This study aims to compare the effectiveness of the Naïve Bayes algorithm in classifying students' anxiety disorders, with and without using the Synthetic Minority Oversampling Technique (SMOTE) method to address data imbalance. The dataset used was obtained from the Kaggle platform and underwent preprocessing stages such as data cleaning, transformation, and handling data imbalance. The model was evaluated using accuracy, precision, recall, and F1-score metrics. The results show that the application of SMOTE improved classification performance for the minority class, although there was a slight decrease in overall accuracy. Therefore, SMOTE proved to help enhance the balance of classification results in the Naïve Bayes model in the context of imbalanced data.]]>
Copyrights © 2025
