Multi-Modal Music Mood Classification

Music mood is a newly emerged metadata type and access point to music information. However, most existing music digital libraries and online repositories do not support categorizing and retrieving music by the mood it expresses. In fact, music mood, due to its subjectivity, has been far from well studied in information science. This dissertation research aims to 1) find out mood categories that are frequently used by real-world music listeners; 2) advance the technology in automatic music mood classification by combining text analysis and audio processing. The results show that a set of music mood categories can be derived from social tags, and combining lyrics and audio improves classification effectiveness and reduces the requirement on training data, both in size and in audio length. The research pushes forward the state-of-the-art on text sentiment analysis and multi-modal classification in the music domain, the proposed method of building large scale ground truth datasets contributes to the evaluation of music information retrieval tasks, and the research findings will help build better music mood classification and recommendation systems by optimizing the interaction of music audio and lyrics