| Sumario: | Background: Over the past 2 years, the Generative Pre‐trained Transformer (GPT), a large language model (LLM) developed by OpenAI, has gained significant momentum across various educational fields. However, its application in physical education (PE) for teaching theoretical knowledge, such as badminton rules, has remained largely underexplored. Objectives: This study aims to evaluate the effectiveness of a GPT‐integrated LINE Bot in facilitating students' learning of badminton rules, compared to traditional teacher‐led question‐and‐answer (Q&A) methods. Methods: Using a quasi‐experimental design, this study divided the participants into an experimental group that used the GPT‐integrated LINE Bot and a control group that received traditional Q&A support. The data collected were analysed quantitatively using a two‐tailed independent samples t‐test, and the results were further supported qualitatively through semi‐structured interviews. Results and Conclusions: The results showed no significant difference in learning outcomes between the two groups, indicating that the GPT‐integrated LINE Bot is equally effective as traditional methods. Positive feedback from participants highlighted the bot's clarity and helpfulness, suggesting its potential as an AI‐supported Q&A tool that can enhance access to clarification in physical education badminton rule instruction. Lay Summary: GPT and other AI tools are increasingly being used in education across a wide range of subjects.The GPT‐integrated LINE Bot produced learning outcomes comparable to those of traditional teacher‐led Q&A.In the experimental group, students were able to ask questions individually and in parallel, resulting in a different questioning structure compared to whole‐class Q&A.GPT‐integrated Q&A systems have the potential to support more equitable access to clarification in physical education badminton rule instruction.
|
|---|