Developing college students’ creative thinking and English story writing through AI-supported collaborative learning
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index; none of the 9 sources its claims cite is checked for support yet.
Abstract
Many English as a foreign language (EFL) students struggle to generate the ideas, express their emotions, and using English to write stories due to the lack of creativity in traditional or teacher-centered writing environment. This study aimed to investigate the effects of AI-supported collaborative learning on EFL college students’ creative thinking and English story writing. A total of 38 EFL college students from two classes, with 16 in the experimental group (AI-supported collaborative writing) and 22 in the control group (traditional writing instruction). The results showed the experimental group improved creativity in fluency, flexibility, and elaboration. The control group made progress in fluency and flexibility; however, effect sizes were small. AI-supported collaborative writing includes story chains, word choice, grammar checking, chatbots, peer feedback and evaluation which promote students’ creative thinking and enhance their English story writing. This study suggests that AI-supported collaborative learning helps college students developing their creative thinking and English story writing.
Overview
CoChat Summary
TL;DR
This study examined AI-supported collaborative writing versus traditional writing instruction among EFL college students, finding that the AI-supported group improved significantly in creative thinking, especially flexibility. The authors conclude that AI-supported collaborative learning can help develop creative thinking and English story writing.
Key findings
- The experimental group improved significantly in fluency (d = 0.72), flexibility (d = 0.96), and elaboration (d = 0.55); flexibility had the highest effect size. Originality did not improve significantly in the experimental group (p = .214, d = 0.32).
- The control group showed modest gains, with the paper reporting that only flexibility (d = 0.48) and fluency (d = 0.54) reached significance; Table 1 also lists control-group originality as significant (p = .012, d = 0.58).
- Questionnaire responses indicated that experimental-group students valued AI for inspiring new ideas, expanding storylines, and encouraging experimentation with story beginnings and character settings; the AI story chain reportedly helped students transcend habitual thinking patterns.
- The paper concludes that AI-supported collaborative writing effectively promoted creative thinking and English story writing compared with traditional writing instruction.
Methods
- Participants were 38 EFL college students from two classes: 16 in the experimental group using AI-supported collaborative writing and 22 in the control group using traditional collaborative writing.
- Both groups received the same teacher instruction with creative thinking and story writing exercises for 18 weeks; the experimental group added AI-supported collaborative learning tools including story chain, word choice, grammatical checking, chatbot, evaluation, and peer feedback.
- Data included pre- and post-Creative Thinking Scales adapted from Lehmkuhl et al. (2021), English story writing first and final drafts, and an open-ended questionnaire; creativity outcomes were analyzed with paired samples t-tests across four dimensions.
Limitations
- The paper does not state a limitations section.
- Evident from the text: the sample was small (N = 38) and unequal across groups (16 experimental, 22 control), limiting generalizability.
- Evident from the text: the reported quantitative results focus on creativity scales, while story writing is illustrated with an example figure and discussed qualitatively rather than analyzed with reported writing scores; no delayed posttest is mentioned.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 0 Not valid · 6 Not checked · 24 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“with only flexibility (d = 0.48) and fluency (d = 0.54) reaching significance.”
§ Developing College Students' Creative Thinking and English Story Writing Through AI-supported Collaborative Learning > Result
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the experimental group, fluency, flexibility, and elaboration improved significantly, with flexibility showing the highest effect size (d = 0.96).”
§ Developing College Students' Creative Thinking and English Story Writing Through AI-supported Collaborative Learning > Result
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The control group showed modest gains, with only flexibility (d = 0.48) and fluency (d = 0.54) reaching significance.”
§ Developing College Students' Creative Thinking and English Story Writing Through AI-supported Collaborative Learning > Result
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“with only flexibility (d = 0.48) and fluency (d = 0.54) reaching significance.”
§ Developing College Students' Creative Thinking and English Story Writing Through AI-supported Collaborative Learning > Result
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In the experimental group, fluency, flexibility, and elaboration improved significantly, with flexibility showing the highest effect size (d = 0.96).”
§ Developing College Students' Creative Thinking and English Story Writing Through AI-supported Collaborative Learning > Result
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
10 more claims
Create a free account to see all 30 claims and to verify the 9 references still open.
- Probably not a substantial claim. 7
- It may state two separate claims as one. 13
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Developing College Students' Creative Thinking and English Story Writing Through AI-supported Collaborative Learning > Result
“The control group showed modest gains, with only flexibility (d = 0.48) and fluency (d = 0.54) reaching significance.”
§ Developing College Students' Creative Thinking and English Story Writing Through AI-supported Collaborative Learning > Discussion and Conclusion
“Originality Exp.16 29.695.63 31.56 4.23 -1.297 .2140.32 Con.22 30.054.59 32.91 6.30 -2.735 .0120.58”
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 2
- [6]6. Fitria, T. N. (2024). Creative writing skills in English: Developing student's potential and creativity. EBONY: Journal of English Language Teaching, Linguistics, and Literature, 4(1), 1-17. https://doi.org/10.37304/ebony .v4i1.10908 · doi:10.37304/ebony
- [11]11. Lehmkuhl, G., von Wangenheim, C. G., Martins-Pacheco, L. H., Borgatto, A. F., & Alves, N. D. C. (2021). SCORE-A model for the self-assessment of creativity skills in the context of computing education in K-12. Informatics in Education, 20(2), 231. https://doi.org/10.15388 /infedu.2021.
Cited by
Brown, C. (2026) · Computer Assisted Language Learning · doi:10.1080/09588221.2026.2737120
Metadata
- Authors
- Wang, S.-C., & Yang, Y.-F.
- Affiliations
- National Yunlin University of Science and Technology (TW)
- Venue
- Proceedings of the International CALL Research Conference
- Publisher
- Castledown Publishers
- Published
- 2025-09-30
- Volume
- 2025
- Pages
- 185-190
- ISSN
- 3083-4252 (ISSN-L)
- OpenAlex
- W4414921514
- Cited by
- 1
- References
- 0
- Citations by year
- 2026: 1
- FWCI
- 23.28
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the International CALL Research Conference (publishedVersion, cc-by-nc)
- Topics
- Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
- Social Sciences › Education › English Language Learning and Teaching
- Social Sciences › Education › Artificial Intelligence in Education
- Keywords
- creative thinking, EFL university students, chatbots, peer feedback, writing fluency, elaboration, grammar checking, word choice
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Developing college students’ creative thinking and English story writing through AI-supported collaborative learning. https://app.cochat.ai/papers/10.29140/97817637116240-24
- The paper
- Wang, S.-C., & Yang, Y.-F. (2025). Developing college students’ creative thinking and English story writing through AI-supported collaborative learning. Proceedings of the International CALL Research Conference. https://doi.org/10.29140/97817637116240-24
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.