Journal of Computational Intelligence Theory and Its Applications

Authors: Rafid O, Vishnu S, Mohammed Ameen Z, Linda Sara Mathew

Abstract: Music has long been a way for people to express their emotions. And because we all have a wide variety of emotions, music comes in all types of styles. Mood is an effective state that plays a significant role in our lives, influencing our behavior, driving social communication, and shifting our consumer preferences. Music can be used to elevate the mood of a person. The tempo, rhythm and pitch of music are managed in areas of the brain that deal with emotions and mood. Even though we are living in an age of digital devices which have many sensors to understand the physical world around them, they are unable to develop insight about the object that matters the most, the user. In our project, this ability of music can be used to develop a mood aware music player which automatically senses the mood of user and uses this prediction to recommend songs in his/her library according to current mood. Our application classifies the user's mood into one of the following: happy, sad, angry, fear and disgust. We use the rhythmic features of the songs to classify them into following moods: happy, feel good and sad. The mood sensor that we implement is a system that recognizes user’s mood from their smartphone usage patterns. Personalized training can be used to learn the user’s mood along with smart phone usage patterns for a specified time period. After the system is trained for this duration, it can then predict the mood of the user and suggest songs to match his/her mood or to elevate the mood of user if he/she is feeling upset or stressed.