Social music discovery: an ethical recommendation system based on friend’s preferred songs

Music recommendation systems have become ubiquitous in today’s world, but they raise ethical concerns related to bias, discrimination, and lack of transparency. To address these issues, we propose a recommendation system that combines content-based and collaborative filtering approaches within three different recommendation algorithms. These algorithms create playlists that mimic the user’s listening habits while identifying similar tracks within the listening histories of the user’s friends. To evaluate the effectiveness of our system, we asked ten participants to rate a total of ninety playlists. The results showed high satisfaction among participants with the playlists generated by two of the proposed recommendation algorithms. Specifically, participants who preferred to stay within their musical comfort zone appreciated one specific recommendation algorithm, while those who were willing to explore new music tended appreciated the other recommendation algorithm. In summary, by leveraging the user’s social connections, our proposed system provides a more transparent and ethical approach to music recommendations. It provides a personalized and enjoyable music discovery experience that considers the nuances of individual musical taste and preferences. These findings suggest the potential impact of our proposal in addressing ethical concerns and enhancing user satisfaction in music recommendation services.