10:00   Oral Session 7-KzZ – Emotional Synthetic Characters 1
Chair: Justine Cassell
10:00
25 mins 		Facial and vocal emotion expression of a personal computer assistant
Judith M. Kessens, Mark A. Neerincx, Rosemarijn Looije, Melanie Kroes, Gerrit Bloothooft
Abstract: The general goal of our research is to develop a personal computer assistant that persuades children to adhere to a healthy lifestyle during daily activities at home. The assistant will be used in three different roles: as companion, educator and motivator. This study investigates whether the effectiveness of the computer assistant with an iCat robot embodiment, can be improved when it expresses emotions (tested for each of the three roles). It shows that emotion expressions can improve the effectiveness of the robot to achieve its role objectives. The improvements that we found are small, however, probably due to a ceiling effect: All subjective measures are rated very positively in the neutral condition, thus leaving little room for improvement. It also showed that the emotional speech was less intelligible, which may limit the robots’ effectiveness.
10:25
25 mins 		Relations between Facial Display, Eye Gaze and Head Tilt: Dominance Perception Variations of Virtual Agents
Nikolaus Bee, Stefan Franke, Elisabeth André
Abstract: In this paper, we focus on facial displays, eye gaze and head tilts to express social dominance. In particular, we are interested in the interaction of different non-verbal cues. We present a study which systematically varies eye gaze and head tilts for five basic emotions and a neutral state using our own graphics and animation engine. The resulting images are then presented to a large number of subjects via a web-based interface who were ask to attribute dominance values to the character shown in the images. First, we analyzed how dominance ratings are influenced by the conveyed emotional facial expression. Further, we take a deeper look in how averted and directed and upward and downward oriented gaze influences the dominance perception.
10:50
25 mins 		Evaluation of Multimodal Sequential Expressions of Emotions in ECA
Radoslaw Niewiadomski, Sylwia Hyniewska, Catherine Pelachaud
Abstract: A model of multimodal sequential facial expressions of emotion for an Embodied Conversational Agent was developed. The model is based on video annotations and on descriptions found in the literature. A language has been derived to describe expressions of emotions as a sequence of facial and body movement signals. An evaluation study of our model is presented in this paper. Animations of 8 sequential expressions corresponding to the emotions - anger, anxiety, cheerfulness, embarrassment, panic fear, pride, relief, and tension - were realized with our model. The recognition rate of these expressions is higher than the chance level making us believe that our model is able to generate recognizable expressions of emotions, even for the emotional expressions not considered to be universally recog- nized.