The DOI matches its Crossref record.
Effects of Using a GPT-based Application for Building EFL Students’ Question-asking Skills
Abstract
With the increasing integration of generative Artificial Intelligence (AI) in education, there is a growing demand for accessible AI-powered platforms for teachers and students. This study examines the efficacy of an online question-making platform using GPT-3.5 generated content to develop Korean students’ question-asking skills in English. Employing a mixed-methods approach, we assessed the platform’s impact on students’ question making abilities and its feasibility in classroom settings. Participants included thirty students from a 4th grade elementary school English classroom in Korea and seven elementary school teachers. Quantitative data were collected through pre- and post-tests measuring students’ question-making skills, while qualitative insights were gathered from semi-structured teacher interviews. Results indicated that the application was able to significantly improve students’ question-making abilities. Thematic analysis of interviews indicated positive perceptions of the platform’s usability and p otential f or l anguage learning. Findings m ay contribute to the growing body of research on using artificial intelligence in L2 education and offer practical insights for educators seeking to leverage advance language models in their instructions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In visual arts, learners employ Midjourney, DALL·E, and related text-to-image tools, repeatedly adjusting prompts to refine visual detail and aesthetics [111-116,132,143]”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [143]
In the citing paper
“Third, GenAI functions as a reflective evaluator. By continually tracking students' help-seeking behaviors and programming dialogues, the system automatically calibrates the granularity of its prompts and generates visual or textual feedback to help students monitor their progress and adjust learning strategies, thus enhancing metacognitive selfregulation [103,141,143,149].”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [143]
Citations
Cites
Still being checked.
Cited by
Park, Y., & Derakhshan, A. (2026) · Language Testing in Asia · doi:10.1186/s40468-026-00429-5 · Cited by 58
Self-citationLin, X., & Tan, H. (2025) · Systems · doi:10.3390/systems13100840 · Cited by 22
Zeng, Y., & Guo, S. (2026) · International Conference on Informatics Education and Computer Technology Applications (IECA) · doi:10.1145/3802133.3802138
Metadata
- Authors
- Sungkyunkwan University, Park, Y., Bum, J., & Lim, D.
- Venue
- Foreign Languages Education
- Published
- 2024-12-31
- Volume
- 31
- Issue
- 4
- Pages
- 51-74
- ISSN
- 1226-4628 (ISSN-L)
- 2384-1427
- OpenAlex
- W4405986517
- Cited by
- 3
- References
- 0
- Citations by year
- 2026: 2 · 2025: 1
- FWCI
- 1.13
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Foreign Languages Education (publishedVersion)
- Topics
- Social Sciences › Education › Artificial Intelligence in Education
- Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
- Social Sciences › Education › English Language Learning and Teaching
- Keywords
- generative AI, GPT-3.5, question-asking skills, EFL learners, Korean students, primary school English, AI-assisted language learning, teacher perceptions, second language acquisition
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.
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: Effects of Using a GPT-based Application for Building EFL Students’ Question-asking Skills. https://app.cochat.ai/papers/10.15334/fle.2024.31.4.51
- The paper
- Sungkyunkwan University, Park, Y., Bum, J., & Lim, D. (2024). Effects of Using a GPT-based Application for Building EFL Students’ Question-asking Skills. Foreign Languages Education. https://doi.org/10.15334/fle.2024.31.4.51
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.