MAKING AGENTS LESS ANNOYING: TOWARDS AN ANIMATED AGENT THAT RESPONDS TO SOCIAL CUES

Animated interface agents have been proposed as a more natural way for the user to interact with computers. Such agents are frequently used in pedagogical and program help applications. While many aspects of social agents have been investigated, that of keeping an appropriate social distance seems to have been overlooked. This ability is coupled with an understanding of when advice is and is not wanted. An agent that gives advice in an Othello program is implemented, which using reinforcement learning adapts its frequency of suggestions to whether or not the user takes the advice. The amount of suggestions that the user can expect is visualized for the user by agent size and position. This agent is compared to one which always gives advice. In the evaluation, test participants experienced that the first agent adapted to their behavior and also found it less distracting.

[1]  Donald A. Norman,et al.  How might people interact with agents , 1994, CACM.

[2]  Gerhard Fischer,et al.  User Modeling in Human–Computer Interaction , 2001, User Modeling and User-Adapted Interaction.

[3]  Patrick Doyle,et al.  When is a Communicative Agent a Good Idea , 1999 .

[4]  Katherine Isbister,et al.  Design and Evaluation of Embodied Conversational Agents: A Proposed Taxonomy , 2002 .

[5]  Ben Shneiderman,et al.  Direct manipulation vs. interface agents , 1997, INTR.

[6]  Geoffrey I. Webb,et al.  # 2001 Kluwer Academic Publishers. Printed in the Netherlands. Machine Learning for User Modeling , 1999 .

[7]  James C. Lester,et al.  Animated pedagogical agents in knowledge-based learning environments , 2001 .

[8]  Brenda Laurel,et al.  Interface agents: metaphors with character , 1997 .

[9]  David N. Chin.  Empirical Evaluation of User Models and User-Adapted Systems , 2001, User Modeling and User-Adapted Interaction.

[10]  Maria Virvou,et al.  Improving agent control for user modeling , 2002, Proceedings First International IEEE Symposium Intelligent Systems.

[11]  H. Noot,et al.  Evaluating ECAs - What and how? , 2006 .

[12]  Thomas Rist,et al.  Adding animated presentation agents to the interface , 1997, IUI '97.

[13]  Lee Sproull,et al.  Using a human face in an interface , 1994, CHI '94.

[14]  G. Lakoff,et al.  Metaphors We Live By , 1980 .

[15]  Daniel S. Weld,et al.  Intelligent Agents on the Internet: Fact, Fiction, and Forecast , 1995, IEEE Expert.

[16]  Eric Horvitz,et al.  The Lumière Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users , 1998, UAI.

[17]  Richard Catrambone,et al.  Embodied Conversational Agents as a UI Paradigm: A Framework for Evaluation , 2002 .

[18]  Kristina Höök,et al.  Evaluating Users' Experience of a Character-enhanced Information Space , 2000, AI Commun..

[19]  Amy L. Baylor,et al.  Agent-Based Learning Environments as a Research Tool for Investigating Teaching and Learning , 2002 .

[20]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[21]  Arthur C. Graesser,et al.  Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents , 1996, ATAL.

[22]  Amy L. Baylor,et al.  Permutations of Control: Cognitive Considerations for Agent-Based Learning Environments , 2001 .

[23]  Pattie Maes,et al.  Agents that reduce work and information overload , 1994, CACM.

[24]  Justine Cassell,et al.  "How about this weather?" Social Dialogue with Embodied Conversational Agents , 2000 .

[25]  R. Duran,et al.  Communicative adaptability: A review of conceptualization and measurement , 1992 .

[26]  Tom Porter,et al.  Creating Lifelike Characters in Pixar Movies. , 2000 .

[27]  Joseph Bates,et al.  The role of emotion in believable agents , 1994, CACM.

[28]  Susanne van Mulken,et al.  The impact of animated interface agents: a review of empirical research , 2000, Int. J. Hum. Comput. Stud..

[29]  Alfred Kobsa,et al.  Generic User Modeling Systems , 2001, User Modeling and User-Adapted Interaction.

[30]  Kristinn R. Thórisson,et al.  The Power of a Nod and a Glance: Envelope Vs. Emotional Feedback in Animated Conversational Agents , 1999, Appl. Artif. Intell..

[31]  Robert D. Smither.  The psychology of work and human performance , 1988 .

[32]  Aude Dufresne,et al.  Modeling the Learner Preferences for Embodied Agents: Experimenting with the Control of Humor , 2002 .

[33]  Clifford Nass,et al.  The media equation - how people treat computers, television, and new media like real people and places , 1996 .

[34]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[35]  Thomas Erickson.  Designing agents as if people mattered , 1997 .

[36]  Amy L. Baylor,et al.  Beyond Butlers: Intelligent Agents as Mentors , 2000 .

[37]  James C. Lester,et al.  The persona effect: affective impact of animated pedagogical agents , 1997, CHI.

[38]  Kerstin Dautenhahn,et al.  The Art of Designing Socially Intelligent Agents: Science, Fiction, and the Human in the Loop , 1998, Appl. Artif. Intell..

[39]  Stuart E. Middleton,et al.  Interface agents: A review of the field , 2002, ArXiv.

[40]  Thomas W. Malone,et al.  Agents for information sharing and coordination: a history and some reflections , 1997 .