Words to Waves: Emotion-Adaptive Music Recommendation System
This addresses the need for more emotionally adaptive music recommendations for users, though it is incremental as it builds on existing Wide and Deep Learning architectures.
The paper tackles the problem of music recommendation systems overlooking emotional context by introducing a framework that uses real-time emotional states inferred from natural language to recommend songs, resulting in a significant improvement in emotional relevance.
Current recommendation systems often tend to overlook emotional context and rely on historical listening patterns or static mood tags. This paper introduces a novel music recommendation framework employing a variant of Wide and Deep Learning architecture that takes in real-time emotional states inferred directly from natural language as inputs and recommends songs that closely portray the mood. The system captures emotional contexts from user-provided textual descriptions by using transformer-based embeddings, which were finetuned to predict the emotional dimensions of valence-arousal. The deep component of the architecture utilizes these embeddings to generalize unseen emotional patterns, while the wide component effectively memorizes user-emotion and emotion-genre associations through cross-product features. Experimental results show that personalized music selections positively influence the user's emotions and lead to a significant improvement in emotional relevance.