Real-time estimation of emotional experiences from facial expressions

The present aim was to develop methods that estimate emotional experiences in real time from the electromyographic activity of two facial muscles: zygomaticus major (activated when smiling) and corrugator supercilii (activated when frowning). Ten subjects were stimulated with a series of emotionally arousing pictures and videos. After each stimulus the subjects rated the valence of their emotional experience on a nine-point bipolar dimensional scale. At the same time the computer estimated the subjects' ratings on the basis of their electrical facial activity during each stimulation with 70 computational models. The models estimated the subjects' ratings either categorically or dimensionally with regression models. The best categorical models were able to estimate negative and positive ratings with an average accuracy of over 70 and 80% for pictures and videos, respectively. The best correlations between the human ratings and machine estimations formed with the regression models were high (r>0.9). These findings indicate that models estimating psycho-emotional experiences on the basis of facial activity can be created successfully in several ways.