Table of Contents
Fetching ...

Learning-by-teaching with ChatGPT: The effect of teachable ChatGPT agent on programming education

Angxuan Chen, Yuang Wei, Huixiao Le, Yan Zhang

TL;DR

This study investigates using a Teachable ChatGPT agent to support learning-by-teaching in programming. By comparing an Experimental Group that teaches a ChatGPT agent to a Control Group learning from videos, the authors assess knowledge gains, programming skills, and self-regulated learning (SRL). Results show improved knowledge and SRL, and better code readability when teaching with ChatGPT, though code correctness did not improve due to the agent's tendency to generate correct code, limiting debugging practice. The work highlights the promise of natural-language, AI-based teachable agents for SRL enhancement and provides design implications for future AI-supported programming education and broader LBT implementations.

Abstract

This study investigates the potential of using ChatGPT as a teachable agent to support students' learning by teaching process, specifically in programming education. While learning by teaching is an effective pedagogical strategy for promoting active learning, traditional teachable agents have limitations, particularly in facilitating natural language dialogue. Our research explored whether ChatGPT, with its ability to engage learners in natural conversations, can support this process. The findings reveal that interacting with ChatGPT improves students' knowledge gains and programming abilities, particularly in writing readable and logically sound code. However, it had limited impact on developing learners' error-correction skills, likely because ChatGPT tends to generate correct code, reducing opportunities for students to practice debugging. Additionally, students' self-regulated learning (SRL) abilities improved, suggesting that teaching ChatGPT fosters learners' higher self-efficacy and better implementation of SRL strategies. This study discussed the role of natural dialogue in fostering socialized learning by teaching, and explored ChatGPT's specific contributions in supporting students' SRL through the learning by teaching process. Overall, the study highlights ChatGPT's potential as a teachable agent, offering insights for future research on ChatGPT-supported education.

Learning-by-teaching with ChatGPT: The effect of teachable ChatGPT agent on programming education

TL;DR

This study investigates using a Teachable ChatGPT agent to support learning-by-teaching in programming. By comparing an Experimental Group that teaches a ChatGPT agent to a Control Group learning from videos, the authors assess knowledge gains, programming skills, and self-regulated learning (SRL). Results show improved knowledge and SRL, and better code readability when teaching with ChatGPT, though code correctness did not improve due to the agent's tendency to generate correct code, limiting debugging practice. The work highlights the promise of natural-language, AI-based teachable agents for SRL enhancement and provides design implications for future AI-supported programming education and broader LBT implementations.

Abstract

This study investigates the potential of using ChatGPT as a teachable agent to support students' learning by teaching process, specifically in programming education. While learning by teaching is an effective pedagogical strategy for promoting active learning, traditional teachable agents have limitations, particularly in facilitating natural language dialogue. Our research explored whether ChatGPT, with its ability to engage learners in natural conversations, can support this process. The findings reveal that interacting with ChatGPT improves students' knowledge gains and programming abilities, particularly in writing readable and logically sound code. However, it had limited impact on developing learners' error-correction skills, likely because ChatGPT tends to generate correct code, reducing opportunities for students to practice debugging. Additionally, students' self-regulated learning (SRL) abilities improved, suggesting that teaching ChatGPT fosters learners' higher self-efficacy and better implementation of SRL strategies. This study discussed the role of natural dialogue in fostering socialized learning by teaching, and explored ChatGPT's specific contributions in supporting students' SRL through the learning by teaching process. Overall, the study highlights ChatGPT's potential as a teachable agent, offering insights for future research on ChatGPT-supported education.

Paper Structure

This paper contains 23 sections, 3 figures, 4 tables.

Figures (3)

  • Figure 1: A sample solution of "eight queens" puzzle that no two queens in the same row, column, or diagonal
  • Figure 2: An example of learners' teaching in solving the "eight queens" puzzle
  • Figure 3: Procedure of the experiment