Evaluating the modeling and use of emotion in virtual humans

Spurred by a range of potential applications, there has been a growing body of research in computational models of human emotion. To advance the development of these models, it is critical that we begin to evaluate them against the phenomena they purport to model. In this paper, we present one methodology to evaluate an emotion model. The methodology is based on comparing the behavior of the computational model against human behavior, using a standard clinical instrument for assessing human emotion and coping. We use this methodology to evaluate the EMA model of emotion [1, 2]. The model did quite well. And, as expected, the comparison helped identify where the model needs further development.

[1]  Christine L. Lisetti,et al.  Automatic facial expression interpretation: Where human-computer interaction, artificial intelligence and cognitive science intersect , 2000 .

[2]  Randall W. Hill,et al.  Toward a New Generation of Virtual Humans for Interactive Experiences , 2002, IEEE Intell. Syst..

[3]  E. Vesterinen,et al.  Affective Computing , 2009, Encyclopedia of Biometrics.

[4]  Stacy Marsella,et al.  Modeling coping behavior in virtual humans: don't worry, be happy , 2003, AAMAS '03.

[5]  Sarit Kraus,et al.  Collaborative Plans for Complex Group Action , 1996, Artif. Intell..

[6]  Mitsuru Ishizuka,et al.  Persona Effect Revisited , 2003, IVA.

[7]  Nicole C. Krämer,et al.  Effects of Embodied Interface Agents and Their Gestural Activity , 2003, IVA.

[8]  Marc Cavazza,et al.  Agents' Interaction in Virtual Storytelling , 2001, IVA.

[9]  E. Peacock,et al.  The stress appraisal measure (SAM): A multidimensional approach to cognitive appraisal , 1990 .

[10]  Thomas Rist,et al.  The automated design of believable dialogues for animated presentation teams , 2001 .

[11]  Randall W. Hill,et al.  Toward the holodeck: integrating graphics, sound, character and story , 2001, AGENTS '01.

[12]  Stacy Marsella,et al.  Interactive pedagogical drama , 2000, AGENTS '00.

[13]  Jim Blythe,et al.  Decision-Theoretic Planning , 1999, AI Mag..

[14]  Kelly G. Shaver,et al.  The attribution of blame : causality, responsibility, and blameworthiness , 1985 .

[15]  Stacy Marsella,et al.  A domain-independent framework for modeling emotion , 2004, Cognitive Systems Research.

[16]  R. Lazarus.  Emotion and Adaptation , 1991 .

[17]  James C. Lester,et al.  Deictic and emotive communication in animated pedagogical agents , 2001 .

[18]  David Moffat,et al.  Where There's a Will There's an Agent , 1995, ECAI Workshop on Agent Theories, Architectures, and Languages.

[19]  Andrew J. Cowell,et al.  Embodiment and Interaction Guidelines for Designing Credible, Trustworthy Embodied Conversational Agents , 2003, IVA.

[20]  Stacy Marsella,et al.  Tears and fears: modeling emotions and emotional behaviors in synthetic agents , 2001, AGENTS '01.

[21]  John Yen,et al.  FLAME—Fuzzy Logic Adaptive Model of Emotions , 2000, Autonomous Agents and Multi-Agent Systems.

[22]  Matthias Scheutz,et al.  AFFECT AND AGENT CONTROL: EXPERIMENTS WITH SIMPLE AFFECTIVE STATES , 2001 .

[23]  S. Marsella,et al.  Interactive Pedagogical Drama for Health Interventions , 2003 .

[24]  Elisabeth André,et al.  The Persona Effect: How Substantial Is It? , 1998, BCS HCI.

[25]  Andrew Ortony,et al.  The Cognitive Structure of Emotions , 1988 .

[26]  C. Elliott.  The affective reasoner: a process model of emotions in a multi-agent system , 1992 .

[27]  Juan David Velásquez,et al.  When Robots Weep: Emotional Memories and Decision-Making , 1998, AAAI/IAAI.