Effects of individual factors on perceived emotion and felt emotion of music: Based on machine learning methods

Abstract

<jats:p> Music emotion information is widely used in music information retrieval, music recommendation, music therapy, and so forth. In the field of music emotion recognition (MER), computer scientists extract musical features to identify musical emotions, but this method ignores listeners’ individual differences. Applying machine learning methods, this study formed relations among audio features, individual factors, and music emotions. We used audio features and individual features as inputs to predict the perceived emotion and felt emotion of music, respectively. The results show that real-time individual features (e.g., preference for target music and mechanism indices) can significantly improve the model’s effect, and stable individual features (e.g., sex, music experience, and personality) have no effect. Compared with the recognition models of perceived emotions, the individual features have greater effects on the recognition models of felt emotions. </jats:p>

The impact of biographical information about a composer on emotional responses to their music

“…The items were grounded in the theoretical literature, but many alternative measurement tools are available. There is also an IMPACT OF BIO 30 ongoing debate as to the difference between perceived and felt emotions (Xu et al, 2020), which should be taken into account in future research.…”

Predicting the Preference for Sad Music: The Role of Gender, Personality, and Audio Features

“…Therefore, Yang et al have advocated to consider the individualities in MER studies [11]. Following Yang's work, many MER studies have investigated individual differences, including testing the effects of individual factors [13] and constructing personalized MER models [97], [98].…”

“…To ensure the stability of perceived emotions, the collected music excerpts were trimmed to 25 seconds in this study. Following the approach of [11], [13], the excerpts were then converted to a uniform format: 22,050 Hz, 16 bits, and mono channel PCM WAV. To objectively evaluate the degree of sadness of the songs, the perceived sadness rating of each excerpt was evaluated on a scale from 1 (not at all) to 5 (very much).…”

“…Referring to the procedure of previous psychological studies [12], [13], the present experiment was designed as follows. After a brief description of the experiment, participants received a listening order containing 12 music excerpts that were randomly selected from our stimuli sets.…”

“…After a brief description of the experiment, participants received a listening order containing 12 music excerpts that were randomly selected from our stimuli sets. The listening order of each participant was independently randomized to minimize the influence of the presentation order [13]. As shown in Figure 3, each excerpt was preceded by 30 seconds of silence and followed by self-report questions.…”