Mood Based Content Recommender: A Full-Stack Web Application Using FastAPI and Frequency-Based Mood Analysis

Mood plays a significant role in influencing an individual’s thoughts, productivity, and overall well-being. This paper presents a Mood Based Content Recommender, a full-stack web application designed to provide personalized content suggestions based on the user’s mood. The system allows users to log their emotional state, which is securely stored using a FastAPI-based backend with database integration. A frequency-based mood analysis algorithm predicts the user’s emotional trend by analyzing recent mood history. Based on the detected mood, the system recommends curated content including songs, motivational quotes, short stories, and movies aimed at improving emotional balance. Additionally, a safe mode detection mechanism identifies repeated negative moods and provides supportive intervention. The application follows a modular three-tier architecture integrating React with TypeScript for the frontend and FastAPI with SQLAlchemy for backend services. The proposed system demonstrates how rule-based analysis combined with structured API architecture can effectively create an emotionally responsive content recommendation platform suitable for users of all age groups.