Towards modeling embodied conversational agent character profiles using appraisal theory predictions in expression synthesis

Abstract

Appraisal theories in psychology study facial expressions in order to deduct information regarding the underlying emotion elicitation processes. Scherer's component process model provides predictions regarding particular face muscle deformations that are attributed as reactions to the cognitive appraisal stimuli in the study of emotion episodes. In the current work, MPEG-4 facial animation parameters are used in order to evaluate these theoretical predictions for intermediate and final expressions of a given emotion episode. We manipulate parameters such as intensity and temporal evolution of synthesized facial expressions. In emotion episodes originating from identical stimuli, by varying the cognitive appraisals of the stimuli and mapping them to different expression intensities and timings, various behavioral patterns can be generated and thus different agent character profiles can be defined. The results of the synthesis process are consequently applied to Embodied Conversational Agents (ECAs), aiming to render their interaction with humans, or other ECAs, more affective.

Modeling the user state for context-aware spoken interaction in ambient assisted living

“…Human dialog knowledge is designed into two layers: domain and discourse knowledge, and it is integrated with the data-driven model in generation time. Recent studies have also addressed important points related to the use of semantic agents, multilevel concepts and behavioral model [47], automatic user-profil generation [50], or using physiological signals to detect natural interactive behaviors [89,100]. A statistical user model supported by a RTree structure and several search spaces is presented in [31].…”

Investigating Facial Animation Production through Artistic Inquiry

“…Studies applying this theory to computer generated faces may yet produce evidence that specific sequences of movement appear more authentic than simultaneous movement [21]. However, this approach also neglects the creative aspect of performance, concentrating on the theorized natural appearance of expressions over time.…”

Special Issue on Emerging Artificial Intelligence Applications and Innovations: Papers from AIAI 2006

“…This special issue, while of course not comprehensive in addressing all the possible fields of Emerging Artificial Intelligence Applications, is indicative of the explosive nature of interdisciplinary research going on in this area. As a result the special issue includes papers from several thematic areas, such as artificial intelligence in medicine [1, 2], pervasive and ubiquitous computing [3,4], emerging multimodal interfaces [5] and personalized human computer interaction [6].As already mentioned, one major area of accelerated growth is the field of computational analysis and artificial intelligence in medicine where a lot of research is done involving the development of diagnostic tools, designed to support the work of medical professionals. Kyriacou et al in [1] investigate the use of several multilevel binary and gray scale morphological analysis algorithms in the assessment of atherosclerotic carotid plaques.…”

“…This special issue, while of course not comprehensive in addressing all the possible fields of Emerging Artificial Intelligence Applications, is indicative of the explosive nature of interdisciplinary research going on in this area. As a result the special issue includes papers from several thematic areas, such as artificial intelligence in medicine [1,2], pervasive and ubiquitous computing [3,4], emerging multimodal interfaces [5] and personalized human computer interaction [6].…”

“…Malatesta et al in [5] propose a mapping of Scherer's component process model to the design and deployment of facial animation in Embodied Conversational Agents (ECAs). Predictions calculated from this model are mapped to particular deformations of facial muscles, encoded in Action Units and then recreated using concepts compatible with emerging multimedia standards.…”