2020

Rumiantcev, Mikhail; Khriyenko, Oleksiy

Nowadays, music platforms provide easy access to large amounts of music. They are working continuously to improve music organization and search management thereby addressing the problem of choice and simplify exploring new music pieces. Recommendation systems gain more and more popularity and help people to select appropriate music for all occasions. However, there is still a gap in personalization and emotions driven recommendations. Music has a great influence on humans and is widely used for relaxing, mood regulation, destruction from stress and diseases, to maintain mental and physical work. There is a wide range of clinical settings and practices in music therapy for wellbeing support. This paper will present the design of the personalized music recommendation system, driven by listener feelings, emotions and activity contexts. With a combination of artificial intelligence technologies and generalized music therapy approaches, a recommendation system is targeted to help people with music selection for different life situations and maintain their mental and physical conditions.