Decoding music-induced experienced emotions using functional magnetic resonance imaging - Preliminary results

Music is known to be a powerful elicitor of emotions. Here, we examined the possibility of decoding musicinduced experienced emotions – affective responses induced in the listener by music stimuli – using functional magnetic resonance imaging (fMRI) data collected while participants listened to various movie soundtrack excerpts. Using a machine learning based classification framework, preliminary results indicate that it is possible to, under certain conditions, decode the arousal (High/Low) and valence (Positive/Negative) of the emotional state experienced during listening. Future work will be aimed at improving methodological issues in order to establish whether these results extend to larger populations and more general types of music stimuli.