Exploiting online music tags for music emotion classification

Abstract

The online repository of music tags provides a rich source of semantic descriptions useful for training emotion-based music classifier. However, the imbalance of the online tags affects the performance of emotion classification. In this paper, we present a novel data-sampling method that eliminates the imbalance but still takes the prior probability of each emotion class into account. In addition, a two-layer emotion classification structure is proposed to harness the genre information available in the online repository of music tags. We show that genre-based grouping as a precursor greatly improves the performance of emotion classification. On the average, the incorporation of online genre tags improves the performance of emotion classification by a factor of 55% over the conventional single-layer system. The performance of our algorithm for classifying 183 emotion classes reaches 0.36 in example-based f-score.

Music Mood Dataset Creation Based on Last FM Tags

“…There is an average of 9.8 tags for each song. Such uneven distribution of tags across tracks has previously been reported in [31] and [15]. Most frequent 30 tags are presented in Table 2.…”

Crowdsourcing Emotions in Music Domain

“…There was an average of 9.8 tags for each song. Such uneven distribution of tags across tracks has previously been reported in [55] and [19]. Top 30 tags are shown in Table 2 together with their appearance frequency.…”

Music Emotion Recognition: From Content- to Context-Based Models

“…An experimentally defined linear combination of the results then outperformed classifiers using individual feature domains. In a more recent study, Lin et al [41] demonstrated that genre-based grouping complements the use of tags in a two-stage multi-label emotion classification system reporting an improvement of 55% when genre information is used. Finally, Schuller [70] et al combined audio features with metadata and Web-mined lyrics.…”