Exploring Learner-Action Timing in a Generative AI Supported EFL Ideathon: A KPT Study in Japan

As generative AI (GenAI) becomes ubiquitous in education, clarifying how learners and educators perceive, and co-design technology is a pressing challenge. This study involved a one-day participatory ideathon in Japan, with nine pre-service English teachers and six high school students co-creating English lesson ideas that integrate GenAI and textbook-based instruction. Using the Keep-Problem-Try framework, participants submitted one hundred sixty-one reflective sticky notes and fifty-five unique lesson proposals. Qualitative analysis was conducted using open and axial coding to identify thematic categories, while the quantitative analysis applied a rubric-based evaluation by GPT-4o across three dimensions: innovativeness, feasibility, and pedagogical alignment, followed by Mann-Whitney U tests for group comparison. The results showed a strong tendency toward experimental approaches, as indicated by the predominance of “Try” entries and a consistent emphasis on UI/UX usability across all categories. These patterns emphasize the foundational role of interface design and highlight the need to control for design-bias when conducting knowledge-based engineering (KBE)-oriented experiments. No statistically significant differences were found between finalist and non-finalist lesson ideas, indicating a convergence in participants’ design perspectives regardless of finalist status. Additionally, pre- and post-workshop surveys analyzed via Wilcoxon signed-rank tests revealed a significant increase in participants’ expectations for GenAI in education (p <.05), confirming the ideathon’s effectiveness in transforming perceptions. These findings offer design guidelines for future KBE experiments with GenAI, particularly regarding baseline conditions and interface specifications.