Generative AI Agent Persona Effects on Pre-service Teachers’ Pedagogical Response Strategies in 3D Teacher Simulation

• In Event: AERA Poster Session Wednesday 9:45am
  In Poster Session: Instructional Technology SIG Poster Presentations

Abstract

The comparison between GPT and rule-based AI architecture revealed that agent persona effects were amplified when pre-service teachers interacted with AI architecture. Pre-service teachers high in Openness showed enhanced questioning behaviors with creative student personas via GPT agents, while conscientious teachers exhibited amplified systematic approaches when encountering both organized and disorganized personas through GenAI. Extraverted students demonstrated increased interactive behaviors with both confident and withdrawn student personas via GPT agents. This amplification occurred because GPT's psychological realism activated deeper person perception processes, making teachers respond more authentically to persona characteristics than with predictable rule-based implementations.

Authors

• Jewoong Moon, University of Alabama

• Jieun Lim, Daegu National University of Education

• Yunseo Lee, University of Wisconsin - Madison

• Gyuri Byun, Seoul National University

• Yeil Jeong, Seoul National University

• Unggi Lee, Korea University