In search of the Horowitz factor
AI Magazine
Modeling emotional content of music using system identification
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
In the study of music emotions, Valence is usually referred to as one of the dimensions of the circumplex model of emotions that describes music appraisal of happiness, whose scale goes from sad to happy. Nevertheless, related literature shows that Valence is known as being particularly difficult to be predicted by a computational model. As Valence is a contextual music feature, it is assumed here that its prediction should also require contextual music descriptors in its predicting model. This work describes the usage of eight contextual (also known as higher-level) descriptors, previously developed by us, to calculate happiness in music. Each of these descriptors was independently tested using the correlation coefficient of its prediction with the mean rating of Valence, reckoned by thirty-five listeners, over a piece of music. Following, a linear model using this eight descriptors was created and the result of its prediction, for the same piece of music, is described and compared with two other computational models from the literature, designed for the dynamic prediction of music emotion. Finally it is proposed here an initial investigation on the effects of expressive performance and musical structure on the prediction of Valence. Our descriptors are then separated in two groups: performance and structural, where, with each group, we built a linear model. The prediction of Valence given by these two models, over two other pieces of music, are here compared with the correspondent listeners' mean rating of Valence, and the achieved results are depicted, described and discussed.