Machine Learning Approaches to Sentiment Analysis of Mental Health Discussions on Platform X

Sentiment analysis on mental health issues is crucial for understanding public perceptions of healthcare services. This study analyzed tweets related to mental health on platform X in 2025 using SVM, Random Forest, and Naive Bayes algorithms. Data was collected through web scraping with Python, then evaluated using a confusion matrix with accuracy, precision, f1-score, and recall metrics. The classification results showed a distribution of sentiment: positive (3,667 tweets), neutral (838 tweets), and negative (704 tweets). A comparative analysis of the three algorithms revealed that SVM achieved the highest accuracy (78.69%), followed by Random Forest (75.04%) and Naive Bayes (70.44%), proving the superiority of SVM in classifying mental health sentiment. These findings provide valuable insights for stakeholders in improving mental healthcare services based on public feedback, while also offering a reference for effective sentiment analysis methods for social media data.