Promoting Discussion and Systems Thinking With Different Role Designs of a Conversational Agent

• In Event: Virtual Agents, Artificial Intelligence, and Automation

Abstract

Conversational agents can facilitate learning. Agents can assume the roles of peers, mentors, or motivators to promote actions similar to human interactions. This study explores how and for whom different role designs of a text-based agent facilitate productive discussion and systems thinking in collaborative settings. Participants included 172 students in 9th grade (ages 13-14). Participants were randomly assigned to groups of five and interacted with no agent, an expert agent, or a less knowledgeable peer agent. Results suggest that both agents facilitated learning of systems mechanisms. We found differences in the agents’ effects on discussion and learning outcomes based on groups’ variation in systems thinking pretest. These findings highlight the importance of role design considerations of agents in group settings.

Author

• Ha Nguyen, Utah State University
  Presenting Author