A Unified Framework for Depression Detection Using ML Algorithms

Abstract

Depression is a common mental health disorder that greatly impacts a person's quality of life and productivity. With the rise of social media and digital communications, analyzing textual data for mental health insights has gained considerable attention. This study presents a comparative analysis of traditional Machine learning algorithms—such as Random Forest, Bagging, Support Vector Classifier (SVC), Logistic Regression, and Naive Bayes. Textual data is preprocessed and vectorized before being fed into the machine learning models, Evaluation is carried out using performance metrics such as accuracy, precision, recall, and F1-score.and compare the models. Experimental results indicate that logistic regression and navie bayes machine learning models Achieve higher accuracy compared to traditional techniques and contextual understanding. This study highlights the potential methods for robust and scalable depression detection systems.