Abstract not found

In this paper, we discuss scripting tools that aim at facilitating the design of web-based interactions with animated characters capable of affective communication. Specifically, two systems are developed. The SCREAM system is a scripting tool that enables authors to create emotionally and socially appropriate responses of animated characters.

This paper introduces a model of interaction between users and animated agents as well as inter-agent interaction that supports basic features of affective conversation. As essential requirements for animated agents' capability to engage in and exhibit affective communication we motivate reasoning about emotion and emotion expression, personality, and social role awareness. The main contribution of our paper is the discussion of so-called `filter programs' that may qualify an agent's expression of its emotional state by its personality and the social context. All of the mental concepts that determine emotion expression, such as emotional state, personality, standards, and attitudes, have associated intensities for fine-tuning the agent's reactions in user-adapted environments.

The growing demand for shopping assistants in E-Commerce was identified by many researchers. Some retailers try to address this need by introducing totally autonomous agents; others make extensive use of human resources, shifting operators from telephone lines to chat-based interactions with online customers. The recently developed 3D Electronic Institutions methodology provides facilities to conveniently combine these two approaches. Initially, an autonomous agent tries to deal with customer’s requests. When the limitations of its intelligence are reached a human operator takes over and satisfies the "out-of-scope " inquiry. At the same time, the agent observes the human operator and learns how to handle similar inquires in the future. We argue that this learning aspect can be realized by means of 3D Electronic Institutions and believe that this "agent training " will be feasible and far more successful than it is possible in nowadays form-based E-Commerce solutions.

... This paper first discusses design principles for animated agents to enhance their effectiveness as tutors, sales persons, or actors, among other roles. It is argued that agents should support their perception as social actors by displaying human-like social cues such as a#ect and gestures. An architecture for emotion-based agents will be described and a simplified version of the model will be illustrated by two interaction scenarios that feature cartoon-style characters and can be run in a web browser. The second focus of this paper is an empirical evaluation of the effect of an affective agent on users' emotional state which is derived from physiological signals of the user. Our findings suggest that an agent with affective behavior may significantly decrease user frustration

Abstract—The use of animated agents in computer based learning environments as a tutoring paradigm can be benefic and increase the learners ’ motivation. This paper discusses the premises under which synthetic agents can be pedagogically effective as tutors in a collaborative learning environment. This research is a follow-up of our previous investigation on usage of agent technology in distance learning environments [5]. This work will highlight a framework for creating believable synthetic agents.

Abstract. An evaluation study using a trailer approach of a Virtual Learning Environment populated with animated characters focusing on physical bullying was carried out with three stakeholder groups, (children, teachers and experts) to examine their attitudes and empathic styles about the characters and storyline believability. Results from 127 children and 95 adults revealed that children expressed the most favourable views towards the characters and the highest levels of believability towards the bullying storyline. Results are discussed in terms of the importance of child-informant processes in leading the design of child-based systems and the use of animated cartoon characters alongside storyline narratives to incite engaging interactions.

Using 3D Virtual Worlds for commercial activities on the Web and the development of human-like sales assistants operating in such environments are ongoing trends of E-Commerce. The majority of the existing approaches oriented towards the development of such assistants are agent-based and are focused on explicit programming of the agents’ decision making apparatus. While effective in some very specific situations, these approaches often restrict agents’ capabilities to adapt to the changes in the environment and learn new behaviors. In this paper we propose an implicit training method that can address the aforementioned drawbacks. In this method we formalize the virtual environment using Electronic Institutions and make the agent use these formalizations for observing a human principle and learning believable behaviors from the human. The training of the agent can be conducted implicitly using the specific data structures called recursive-arc graphs.

This paper introduces a model of user-agent and interagent interaction that supports basic features of affective communication. As essential requirements for animated agents' capability to engage in social interaction, we motivate reasoning about emotion and emotion expression, personality, and social role awareness. A (rather standard) appraisal program is employed to derive the agent's emotional state. The novel aspect of our approach is the introduction of a filter program that qualifies the agent's expression of its emotional state by its personality and more importantly, by the social setting in which the conversation takes place. This allows an agent to suppress an emotion, if the expression of the emotion would defeat a higher-order goal. We also discuss rudimentary mechanisms of social feedback.

Abstract. Believability is a key issue for virtual agents. Most of the authors agree that emotional behavior and personality have a high impact on agents ’ believability. The social capacities of the agents also have an effect on users ’ judgment of believability. In this paper we analyze the role of plausible and/or socially appropriate emotional displays on believability. We also investigate how people judge the believability of the agent, and whether it provokes social reactions of humans toward the agent. The results of our study in the domain of software assistants, show that (a) socially appropriate emotions lead to higher perceived believability, (b) the notion of believability is highly correlated with the two major socio-cognitive variables, namely competence and warmth, and (c) considering an agent believable can be different from considering it human-like.