Multi-modal Music Data Classification and Music Product Recommendation Method Based on Intelligent Algorithms

The current music platforms generally suffer from issues such as the lack of emotional music data classification, insufficient multi-modal data fusion, incomplete user profiling, and simplistic recommendation methods. To address these problems, this paper proposes a multi-modal music data classification and music product recommendation method based on intelligent algorithms. The Hevner Emotion Model is adopted for music classification, fusing audio, lyrics, and playlist multi-modal data to achieve precise music product classification. A comprehensive user profiling system is constructed, and automatic matching and recommendation between users and music products are realized. These methods effectively enhance the accuracy of music classification, enrich user profiling, and enable personalized recommendations tailored to individual preferences, thereby improving the marketing and operational efficiency of music products.