Simulated Approximation of Practices in Mathematics: Development of Artificial Intelligence–Based Chatbot

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

Abstract

Our goal was to develop an Artificial-Intelligence based chatbot that engaged preservice teachers' (PSTs) in an authentic, meaningful, and open-ended teaching situation to enhance PSTs' responsive teaching skills, specifically questioning skills through approximations of practice. The chatbot was designed to act as a virtual student who displayed misconceptions on the topic of fractions. By employing design-based research, we examined design features and structure of the chatbot, coverage of users’ input, and PSTs’ questioning patterns. Two iterations of design, implementation, and evaluation took place in an elementary mathematics education methods course. Through multiple iterations, we found that certain design features could lead to improved questioning patterns and user perceptions. Implications, design features, and limitations are discussed.

Authors

• Dabae Lee, Kennesaw State University
  Presenting Author

• Sheunghyun Yeo, Daegu National University of Education
  Presenting Author

• Eunbae Lee, Kyung Hee University
  Presenting Author