Exploring Learner-Action Timing in a Generative AI Supported EFL Ideathon: A KPT Study in Japan
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".