A User-Modeling Approach to Build User´s Psycho-Physiological Maps of Emotions using Bio-Sensors

Near to real-time emotion recognition is a promising task for human-computer interaction (HCI) and human-robot interaction (HRI). Using knowledge about the user´s emotions depends upon the possibility to extract information about users´ emotions during HCI or HRI without explicitly asking users about the feelings they are experiencing. To be able to sense the user´s emotions without interrupting the HCI, we present a new method applied to the emotional experience of the user for extracting semantic information from the autonomic nervous system (ANS) signals associated with emotions. We use the concepts of 1^st person - where the subject consciously (and subjectively) extracts the semantic meaning of a given lived experience, (e.g. `I felt amused´) - and 3^rd person approach - where the experimenter interprets the semantic meaning of the subject´s experience from a set of externally (and objectively) measured variables (e.g. galvanic skin response measures). Based on the 3^rd person approach, our technique aims at psychologically interpreting physiological parameters (skin conductance and heart rate), and at producing a continuous extraction of the user´s affective state during HCI or HRI. We also combine it with the 1^st person approach measure which allows a tailored interpretation of the physiological measure closely related to the user own emotional experience