[Emotional and social robots for care, ethical challenges and issues]. / Des robots affectifs et sociaux pour le soin, enjeux et problématiques éthiques.

The arrival of robots in our society often arouses fantasies and fears. Emotional and social robots are already being used in healthcare. Ethical analysis is necessary to regulate the use of these objects which are able to simulate dialogues, appearing to feel emotions and to be capable of learning.

Global stress response during a social stress test: impact of alexithymia and its subfactors.

OBJECTIVES: Alexithymia is a personality trait characterized by difficulties in identifying, describing and communicating one's own emotions. Recent studies have associated specific effects of this trait and its subfactors with hypothalamo-pituitary-adrenal (HPA) axis markers during stress. The aim of this study was to analyze the association between alexithymia and its subfactors with HPA and sympatho-adrenal medullar (SAM) activity. Stress was induced experimentally using a public-speaking paradigm. Salivary cortisol, alpha-amylase (AA), chromogranin A (CgA) and heart rate (HR) were collected during the defined periods of baseline, stress, and recovery in 19 males and 24 female healthy university students. RESULTS: Subjects reacted to the stressor with a significant cortisol and SAM response. Subjects scoring high on alexithymia reacted significantly more intensely than low scorers in basal anticipatory as well as peak cortisol and area under the curve. Regression analyses revealed that the increased HPA activity was related to only one alexithymia subfactor, the difficulty in differentiating feelings and distinguishing them from bodily sensations and emotion arousal. CONCLUSION: Alexithymia and its subfactors were specifically related to cortisol responses. This research should be replicated with more subjects and should take into account more parameters reflecting sympathetic and/or parasympathetic activation, as well as HPA axis. Factors such as coping strategies and the perception of the situation as a challenge have also to be explored.

Challenges in real-life emotion annotation and machine learning based detection.

Since the early studies of human behavior, emotion has attracted the interest of researchers in many disciplines of Neurosciences and Psychology. More recently, it is a growing field of research in computer science and machine learning. We are exploring how the expression of emotion is perceived by listeners and how to represent and automatically detect a subject's emotional state in speech. In contrast with most previous studies, conducted on artificial data with archetypal emotions, this paper addresses some of the challenges faced when studying real-life non-basic emotions. We present a new annotation scheme allowing the annotation of emotion mixtures. Our studies of real-life spoken dialogs from two call center services reveal the presence of many blended emotions, dependent on the dialog context. Several classification methods (SVM, decision trees) are compared to identify relevant emotional states from prosodic, disfluency and lexical cues extracted from the real-life spoken human-human interactions.