![]() On the other hand, with the development of natural language processing (NLP) technology, different lyric features have been widely extracted and analyzed in music emotion recognition (MER) studies ( e.g., Malheiro et al., 2016a Malheiro et al., 2016b Delbouys et al., 2018), a field investigating computational models for detecting music emotion ( Aljanaki, Yang & Soleymani, 2017 Chen et al., 2015a). While lyric structures and features have been rarely studied, melodic information has been processed in previous psychology studies ( Gabrielsson, 2016 Swaminathan & Schellenberg, 2015 Xu et al., 2020a). Music emotion studies related to lyrics have often focused on investigating the differences between the presence and absence of lyrics ( Ali & Peynircioğlu, 2006 Brattico et al., 2011 Yu et al., 2019a Yu et al., 2019b), the effects of consistency or differences in melodic and lyrical information ( Morton & Trehub, 2001 Vidas et al., 2020), or the effects of lyrics with different meanings ( Batcho et al., 2008 Stratton & Zalanowski, 1994). ![]() Although melodic information may be more dominant than lyrics in conveying emotions ( Ali & Peynircioğlu, 2006), investigating the relationship between lyrical structure and the perceived emotion of music in detail is still necessary. (1998) proved that melodic and lyrical components in music are processed independently. Previous works have shown that sound features were highly correlated with music emotions ( Gabrielsson, 2016 Yang, Dong & Li, 2018), but the lyric features have been relatively less discussed. For example, psychologists have made considerable progress in revealing structural factors ( e.g., tempo, pitch, and timbre), indicating different emotional expressions ( Gabrielsson, 2016), and computer scientists have focused on extracting features from audio (audio most commonly refers to sound, as it is transmitted in signal form e.g., Mel-frequency cepstrum coefficients and Daubechies wavelet coefficient histograms) to automatically identify music emotion ( Yang, Dong & Li, 2018). Most of the related studies have focused on investigating the association between musical structure and perceived emotions. Therefore, the relationship between music and perceived emotional expression has attracted increasing academic attention in recent decades ( Swaminathan & Schellenberg, 2015). The pursuit of emotional experience is a vital motivation for listening to music ( Juslin & Sloboda, 2001 Juslin & Laukka, 2004), and the ability to convey emotions ensures the important role of music in human life ( Yang, Dong & Li, 2018). Unlike the uselessness of the lyric features in the arousal recognition model, several lyric features, such as the usage frequency of words related to sadness, positive emotions, and tentativeness, played important roles in the valence recognition model. ![]() Finally, by calculating the feature importance to interpret the MER models, we observed that the audio features played a decisive role in the recognition models of both perceived arousal and perceived valence. The performance of random forest regressions reveals that, for the recognition models of perceived valence, adding lyric features can significantly improve the prediction effect of the model using audio features only for the recognition models of perceived arousal, lyric features are almost useless. Second, we used audio and lyric features as inputs to construct music emotion recognition (MER) models. The perceived valence of music was negatively correlated with the proportion of negative emotion words. First, correlation analysis shows that, for example, the perceived arousal of music was positively correlated with the total number of lyric words and the mean number of words per sentence and was negatively correlated with the proportion of words related to the past and insight. Using linguistic inquiry and word count (LIWC) technology to extract lyric features in 2,372 Chinese songs, this study investigated the effects of LIWC-based lyric features on the perceived arousal and valence of music. Although psychologists and computer scientists have made considerable progress in revealing the association between musical structure and the perceived emotions of music, the features of lyrics are relatively less discussed. Melody and lyrics, reflecting two unique human cognitive abilities, are usually combined in music to convey emotions.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |