Automated Personalized Mood-Based Song Selector

Music and weather significantly influence individuals’ moods, playing pivotal roles in daily life. This research explores integrating music and weather data to enhance the driving experience by dynamically adjusting the music playlist based on the driver's mood and the current weather conditions, considering the potential hazards of manual song selection while driving. The research addresses the challenge of maintaining a consistent mood during long drives, which can be significantly influenced by the music played. We propose a solution that involves an AI-integrated application utilizing facial emotion recognition to gauge the driver's mood and weather data to infer the appropriate mood for the music. This mood detection system aims to select songs matching the combined mood, enhancing the overall driving experience. We employ machine learning models for emotion detection from facial expressions and weather data, employing binary and multiclass classification techniques. The study contributes to personalized music recommendation systems by introducing a novel approach that considers external environmental factors, demonstrating the potential for further advancements in mood-based music recommendation systems.