Exploring Dialogue Patterns in Argumentation with Pre-Set ChatGPT Personas

Authors

  • Seunmin EUN Department of Education, Seoul National University Author
  • Seonmin JIN Department of Social Studies Education, Seoul National University Author

DOI:

https://doi.org/10.58459/icce.2024.5064

Abstract

This study explores the impact of interacting with two Al personas, such as an American male CEO of an IT startup, and a Muslim university female student, on thought expansion and learners' argumentative writing. The study with ten participants combined quantitative and qualitative analyses to assess the impact of Al persona interactions. Consistent improvements in writing scores were observed following interactions with these Al personas, suggesting a potentially positive effect on writing ability. In addition, the analysis of dialogue patterns revealed three stages: exploration, calibration, and reinforcement. These stages highlight how learners engaged with diverse perspectives, integrated new ideas, and strengthened their critical thinking. While the findings are promising, the small sample size necessitates further research with larger cohorts to validate these preliminary results. Future studies should focus on refining these interaction strategies to enhance critical thinking and writing skills in educational settings.

Downloads

Download data is not yet available.

Downloads

Published

2024-11-25

How to Cite

Exploring Dialogue Patterns in Argumentation with Pre-Set ChatGPT Personas. (2024). International Conference on Computers in Education. https://doi.org/10.58459/icce.2024.5064