Embodied conversational agents as peer collaborators: Effects of multiplicity and modality

The goal of this study was to investigate the efficient use of role-taking embodied conversational agents in the facilitation of creative cognition during collaborative activities. Two factors were investigated through an experimental design addressing the number of conversational agents (one vs. two), and method of communication (voice vs. text). Participants engaged in a simple interpretation game with embodied conversational agents. The agents made suggestions on the quality of the participants' interpretations. We investigated how the two factors enhanced the quality and quantity of interpretations in collaborative activities. Results showed that the use of single agents and text-based interfaces enhanced the quantity of the creative interpretations, and the synergy created by the use of multiple agents along with a voice communication method enhanced the quality of creative interpretations. These results suggest that the number of agents and the method of communication are important in the effective use of embodied conversational agents as collaborating peers.

[1]  Anna Borg,et al.  Principles of Regulating Interaction in Teams Practicing Face-To-Face Communication Versus Teams Practicing Computer-Mediated Communication , 2005 .

[2]  Lucy Gilson,et al.  Virtual Teams: What Do We Know and Where Do We Go From Here? , 2004 .

[3]  Steven M. Smith,et al.  Constraining effects of examples in a creative generation task , 1993, Memory & cognition.

[4]  Joseph Weizenbaum,et al.  and Machine , 1977 .

[5]  Arthur C. Graesser,et al.  Self-Regulated Learning in Learning Environments With Pedagogical Agents That Interact in Natural Language , 2010 .

[6]  Carolyn Penstein Rosé,et al.  Architecture for Building Conversational Agents that Support Collaborative Learning , 2011, IEEE Transactions on Learning Technologies.

[7]  Sara Kiesler,et al.  Social psychological aspects of computer-mediated communication , 1984 .

[8]  E. Vance Wilson,et al.  Perceived effectiveness of interpersonal persuasion strategies in computer-mediated communication , 2003, Comput. Hum. Behav..

[9]  Debra K. Meyer,et al.  Discovering Emotion in Classroom Motivation Research , 2002 .

[10]  Yasuhiko Kitamura,et al.  Influence of social relationships on multiagent persuasion , 2008, AAMAS.

[11]  Yan Bing Zhang,et al.  Social Interactions Across Media , 2004 .

[12]  Luca Milani,et al.  Computer-mediated communication and persuasion: Peripheral vs. central route to opinion shift , 2008, Comput. Hum. Behav..

[13]  Jane E. Klobas,et al.  Evaluation of the efficacy of collaborative learning in face-to-face and computer-supported university contexts , 2006, Comput. Hum. Behav..

[14]  Solomon E. Asch,et al.  Opinions and Social Pressure , 1955 .

[15]  John T. Cacioppo,et al.  The Elaboration Likelihood Model of Persuasion , 1986, Advances in Experimental Social Psychology.

[16]  Yanghee Kim,et al.  Simulating Instructional Roles through Pedagogical Agents , 2005, Int. J. Artif. Intell. Educ..

[17]  Clifford Nass,et al.  Experimental Tests of Normative Group Influence and Representation Effects in Computer-Mediated Communication: When Interacting Via Computers Differs from Interacting With Computers. , 2002 .