Cognitive Therapy and Routine Recommendation System (CTRRS): An AI-Driven Approach for Mental Health

Depression detection and management is an important research field nowadays. In this research work, Cognitive Therapy and Routine Recommendation System (CTRRS) is proposed. It automates the process of detecting depression and provides personalized mental health recommendations using a Random Forest model for healthcare activities and a Long Short-Term Memory (LSTM) model for sentiment analysis. The LSTM architecture includes dense layers, bidirectional LSTM layers, and embedding layers, with term frequency-inverse document frequency (TF-IDF) vectorization and early stopping to prevent overfitting. Furthermore, a Voting Classifier improves classification performance by combining the advantages of multiple models. The system's evaluation is centered on accuracy, precision, recall, and F1-score, with confusion matrices offering in-depth analysis. Finally, CTRRS uses a cosine similarity algorithm to customize content to user preferences, increasing engagement. The study integrates machine learning and deep learning by employing a Random Forest model for healthcare activity recommendations and an LSTM model for sentiment analysis and depression detection. This combination leverages the strengths of both approaches to enhance the system's overall performance. Additionally, ensemble learning techniques such as bagging, boosting, and stacking are utilized to balance performance trade-offs and improve predictive accuracy. The LSTM model achieved 96.38% accuracy, 98.10% precision, 94.50% recall, and a 96.27% F1-score, which are important findings. Through user-friendly visualizations (PHQ-9 survey responses, word clouds highlighting frequent terms in depression-related texts, bar charts displaying top TF-IDF features, and confusion matrices for model performance evaluation), CTRRS enables users to monitor their progress in terms of mental health and compliance with recommendations. This research advances mental health care by providing a solution that is stigma-free, scalable, and accessible.