Generative AI-based Writing Feedback Model Development
Jin‐Young Choi · 2024
This study aimed to develop a systematic writing feedback model that reduces the burden on teachers in the writing process while allowing students to receive individualized feedback using generative AI. Thirteen experts were recruited and a Delphi survey was conducted. The results were as follows. First, we identified a writing process for utilizing generative AI and a feedback structure for that process. Second, we finalized the argumentative writing test and its evaluation factors and detailed scoring criteria to be applied to this model. Third, we added examples of generative AI question types and prompts to provide concrete examples of the model. The implications are as follows. First, generative AI has the potential to drive self-reflective feedback from students during the writing process. Second, generative AI can reduce teacher fatigue and provide more personalized feedback. Finally, we propose a concrete feedback model for generative AI in education. However, this study had a limitation in that it did not confirm the effect through the application of a practical model. Therefore, we will continue to conduct follow-up research.