Developing a user-specific affect model for classifying music based on timbral content

• Main Authors: Avisado, Hal Gino P., Cocjin, John Vincent U., Gaverza, Joshua Alexie M.
• Format: text
• Language: English
• Published: Animo Repository 2010
• Subjects: Music > Emotion; Tone color (Music); Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/etd_bachelors/10465
• Institution: De La Salle University

The relationship between timbre and emotion has not yet been explored in-depth. Specifically, a user-specific affect model for classifying music by timbral content has yet to be created. Such a model would provide an insight into the specific of the relationship between timbre and emotion. Several steps are taken on the construction of such a model, namely the corpora building, the classification, and the prototyping. Preliminary data mining and data analysis was done with the help of Weka. The type and number of the instruments used was also taken into account, and normalization and principal components analysis was also used in analyzing the data. The verification and classification of the emotional response from all the subjects and analyzing the timbral content of those pieces. Some pieces were found whose timbral content induces consistent emotional responses from all the subjects.