ECA as User Interface Paradigm

A strong debate has ensued in the computing community about whether Embodied Conversational Agents (ECAs) are beneficial and whether we should pursue this direction in interface design. Proponents cite the naturalness and power of ECAs as strengths, and detractors feel that ECAs disempower, mislead, and confuse users. As this debate rages on, relatively little systematic empirical evaluation on ECAs is actually being performed, and the results from this research have been contradictory or equivocal. We propose a framework for evaluating ECAs that can systematize the research. The framework emphasizes features of the agent, the user, and the task the user is performing. Our goal is to be able to make informed, scientific judgments about the utility of ECAs in user interfaces. If intelligent agents can be built, are there tasks or applications for which an ECA is appropriate? Are there characteristics (in appearance, in personality, etc.) the ECA should have? What types of users will be more productive and happy by interacting with an ECA? Our initial experiment within this framework manipulated the ECA’s appearance (realistic human versus iconic object) and the objectivity of the user’s task (editing a document versus deciding what to pack on a trip). We found that the perception of the ECA was strongly influenced by the task while features of the ECA that we manipulated had littlee ect.

[1]  Ben Shneiderman,et al.  Direct manipulation versus agents: paths to predictable, controllable, and comprehensible interfaces , 1997 .

[2]  Pattie Maes,et al.  Interface agents , 1996, CHI Conference Companion.

[3]  David Wood,et al.  The effect of task conditions on the comprehensibility of synthetic speech , 2000, CHI.

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

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

[6]  Justine Cassell,et al.  Relational agents: a model and implementation of building user trust , 2001, CHI.

[7]  F. Paas,et al.  Cognitive Architecture and Instructional Design , 1998 .

[8]  John T. Stasko,et al.  Be Quiet? Evaluating Proactive and Reactive User Interface Assistants , 2003, INTERACT.

[9]  C. Nass,et al.  How “Real” Are Computer Personalities? , 1996 .

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

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

[12]  Jun Ohya,et al.  The representation of agents: anthropomorphism, agency, and intelligence , 1996, CHI Conference Companion.

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

[14]  Clifford Nass,et al.  Anthropocentrism and computers , 1995, Behav. Inf. Technol..

[15]  R. Mayer,et al.  Maximizing Constructivist Learning From Multimedia Communications by Minimizing Cognitive Load , 1999 .

[16]  Jeffrey M. Bradshaw,et al.  An introduction to software agents , 1997 .

[17]  Jane Klobas,et al.  The relationship between visual abstraction and the effectiveness of a pedagogical character-agent , 2002, AAMAS 2002.

[18]  Arne Jönsson,et al.  Wizard of Oz studies -- why and how , 1993, Knowl. Based Syst..

[19]  Gregory A. Sanders,et al.  Measurement and evaluation of embodied conversational agents , 2001 .

[20]  Clifford Nass,et al.  Does computer-generated speech manifest personality? an experimental test of similarity-attraction , 2000, CHI.

[21]  Clifford Nass,et al.  Computers are social actors , 1994, CHI '94.

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

[23]  Mervyn A. Jack,et al.  Experimental assessment of the effectiveness of synthetic personae for multi-modal e-retail applications , 2000, AGENTS '00.

[24]  P. Costa,et al.  Validation of the five-factor model of personality across instruments and observers. , 1987, Journal of personality and social psychology.

[25]  S. Joy Mountford,et al.  The Art of Human-Computer Interface Design , 1990 .

[26]  Justine Cassell,et al.  Embodied conversational interface agents , 2000, CACM.

[27]  Akikazu Takeuchi,et al.  Situated facial displays: towards social interaction , 1995, CHI '95.

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

[29]  John Sculley,et al.  The relationship between business and higher education: a perspective on the 21st century , 1989, CACM.

[30]  Byron Reeves,et al.  The effects of animated characters on anxiety, task performance, and evaluations of user interfaces , 2000, CHI.

[31]  Michael R. Genesereth,et al.  Software agents , 1994, CACM.

[32]  J. Cassell,et al.  Embodied conversational agents , 2000 .

[33]  Tomoko Koda,et al.  Agents with faces : a study on the effects of personification of software agents , 1996 .

[34]  Jaron Lanier.  Agents of alienation , 1995, INTR.

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