<![CDATA[Depression is one of the most serious mental health problems among college students, but it often goes unnoticed due to social stigma and limited access to psychological services. This study aims to apply the Naïve Bayes algorithm to predict depression in college students based on various factors, such as academic pressure, sleep duration, eating habits, financial stress, and family history of mental disorders. The model was built using 502 data obtained from the Kaggle platform, through the stages of data preprocessing, transformation, classification using Gaussian Naïve Bayes, and evaluation using a confusion matrix. The implementation process was carried out in Google Colab using the scikit-learn library. The evaluation results showed very good model performance with an accuracy of 97%, precision of 96%, recall of 98%, and F1-score of 97%. These findings indicate that the Naïve Bayes algorithm can be used effectively as an anonymous and efficient early screening tool for depression and has the potential to support increased awareness and mental health interventions in the college student environment.]]>
Copyrights © 2025
