A Personalized and Context Aware Music Recommendation System

• Published in: Social Computing and Social Media. Participation, User Experience, Consumer Experience, and Applications of Social Computing pp. 616 - 627
• Main Authors: Wishwanath, Champika H. P. D., Weerasinghe, Supuni N., Illandara, Kanishka H., Kadigamuwa, A. S. T. M. R. D. S., Ahangama, Supunmali
• Format: Book Chapter
• Language: English
• Published: Cham Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Music recommendation; Personalized recommendation; Social media
• ISBN: 3030495752; 9783030495756
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-49576-3_45

People listen to music as it expresses and induce emotions. Considering millions of songs available in online streaming services, it is difficult to identify the most suitable song for an emotion of a user. Most of the music recommendation systems available today, are based on user ratings and acoustic features of the songs. Those systems are unable to address the cold start problem and rating diversity. Furthermore, song preferences will be altering based on the current mood of the users. If these problems were not addressed, then these online services will fail to achieve user satisfaction. To cope with those problems, this paper proposes a novel music recommendation approach that utilizes social media content such as posts, comments, interactions, etc. and recommend them with the most relevant songs to relax their mind considering the current mood (happy, sad, calm and angry). The current mood and the preferences are extracted from the social media profile of the users. Then the songs were classified to moods based on the lyrics and audio of the songs.