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

摘要

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 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> person - where the subject consciously (and subjectively) extracts the semantic meaning of a given lived experience, (e.g. `I felt amused') - and 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> 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 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> 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 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">st</sup> person approach measure which allows a tailored interpretation of the physiological measure closely related to the user own emotional experience