The use of ChatGPT as a learning tool to improve foreign language writing in a multilingual and multicultural classroom
Open accessThe DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Abstract
The association of Artificial Intelligence (AI) and education has attracted researchers’ attention, as it is very beneficial for learners affecting the whole teaching procedure. ChatGPT, an AI language model developed by OpenAI and based on the Generative Pre-trained Transformers (GPT)-3.5 architecture, though newly introduced in November 2022, became very popular even within the first two months. Researchers have already explored and acknowledged the affordances of ChatGPT for language learning and teaching. In this context, the study aimed to examine the effectiveness of ChatGPT as a feedback tool on foreign language writing, especially for socially vulnerable populations, such as refugees/migrants, who face extra language difficulties. The study was conducted in a Junior High School (Gymnasium) classroom in an urban city in south Greece, which consisted of 8 students with a migrant/refugee background aged 15 years old who were attending German as a foreign language learning. The focus of the study was to analyze how the use of ChatGPT could improve foreign language writing in terms of vocabulary and grammar. After the students' first writing attempt, we asked ChatGPT to enhance the vocabulary and grammar of the texts. In contrast, the students received an improved version in terms of language and grammar, and then, they were asked to produce another writing piece of work on a similar topic to their first attempt. The study results indicated an increase in the total number of words, the unique words and the average word number per sentence in the improved version of their work. Overall, the study results were promising, indicating that ChatGPT could act as a language learning tool and support the teaching procedure, especially for students with a refugee/migrant background. However, further research is needed to investigate its use and effectiveness in diverse contexts.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290
“Multiliteracies”: New Literacies, New Learning
Cope, B., & Kalantzis, M. (2009) · Pedagogies: An International Journal · doi:10.1080/15544800903076044 · Cited by 1,490
ChatGPT for Language Teaching and Learning
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023) · RELC Journal · doi:10.1177/00336882231162868 · Cited by 1,371 · cited 6×
“Moreover, a critical stance is required on the learners’ part, as the information’s accuracy and the responses provided by ChatGPT should always be checked (Kim et al., 2023; Kohnke et al., 2023).”
BackgroundMethodInfluentialChatGPT User Experience: Implications for Education
Zhai, X. (2023) · doi:10.2139/ssrn.4312418 · Cited by 935 · cited 1×
“Its ability to work on complicated tasks that require human intelligence, such as answering exam-style questions in business, law, and medicine or writing academic texts, has placed it as an innovative learning tool, attracting researchers’ interest (Zhai, 2022).”
BackgroundHuang, W., Hew, K. F., & Fryer, L. K. (2022) · Journal of Computer Assisted Learning · doi:10.1111/jcal.12610 · Cited by 830
Impact of ChatGPT on learners in a L2 writing practicum: an exploratory investigation
Yan, D. (2023) · Education and Information Technologies · doi:10.1007/s10639-023-11742-4 · Cited by 713 · cited 3×
“Considering the first promising findings of the use of ChatGPT as a language learning tool (e.g., Hong, 2023; Kim et al., 2023; Kohnke et al., 2023; Yan, 2023), the aim of the present study, which was a pilot study, was to explore how the use of ChatGPT could improve foreign language writing in terms of vocabulary and…”
BackgroundResultMathematical Capabilities of ChatGPT
Frieder, S., Pinchetti, L., Chevalier, A., Griffiths, R.-R., Salvatori, T., Lukasiewicz, T., Petersen, P. C., & Berner, J. (2023) · arXiv · doi:10.48550/arxiv.2301.13867 · Cited by 385
Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
Jiao, W., Wang, W., Huang, J.-T., Wang, X., Shi, S., & Tu, Z. (2023) · arXiv · doi:10.48550/arxiv.2301.08745 · Cited by 317
Will ChatGPT get you caught? Rethinking of Plagiarism Detection
Khalil, M., & Er, E. (2023) · doi:10.35542/osf.io/fnh48 · Cited by 259
ChatGPT’s inconsistent moral advice influences users’ judgment
Krügel, S., Ostermaier, A., & Uhl, M. (2023) · Scientific Reports · doi:10.1038/s41598-023-31341-0 · Cited by 183
Cited by
Sharma, S., Mittal, P., Kumar, M., & Bhardwaj, V. (2025) · Discover Sustainability · doi:10.1007/s43621-025-01094-z · Cited by 165
Bui, N. M., & Barrot, J. S. (2025) · Education and Information Technologies · doi:10.1007/s10639-024-12891-w · Cited by 113
“Studies on the utilization of ChatGPT for L2 writing have recently been building up (e.g., Athanassopoulos et al., 2023; Javier & Moorhouse, 2023; Marzuki et al., 2023; Su et al., 2023).”
Aravantinos, S., Lavidas, K., Voulgari, I., Papadakis, S., Karalis, T., & Komis, V. (2024) · Education Sciences · doi:10.3390/educsci14070744 · Cited by 110
Self-citationTeachers’ perspectives on artificial intelligence in education
Uygun, D. (2024) · Advances in Mobile Learning Educational Research · doi:10.25082/amler.2024.01.005 · Cited by 99
Woo, D. J., Wang, D., Guo, K., & Susanto, H. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-12819-4 · Cited by 104
“On the other hand, Athanassopoulos et al. (2023) examined Chat-GPT’s effectiveness as a writing vocabulary and grammar feedback tool for eight, 15-year old migrants and refugees.”
Metadata
- Authors
- Athanassopoulos, S., Manoli, P., Gouvi, M., Lavidas, K., & Komis, V.
- Venue
- Advances in Mobile Learning Educational Research
- Publisher
- Syncsci Publishing Pte., Ltd.
- Published
- 2023-08-30
- Volume
- 3
- Issue
- 2
- Pages
- 818-824
- ISSN
- 2737-5676 (ISSN-L)
- OpenAlex
- W4386292090
- Cited by
- 148
- References
- 13
- FWCI
- 34.54
- Type
- journal article
- Language
- en
- Open access
- hybrid
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: The use of ChatGPT as a learning tool to improve foreign language writing in a multilingual and multicultural classroom. https://app.cochat.ai/papers/10.25082/amler.2023.02.009
- The paper
- Athanassopoulos, S., Manoli, P., Gouvi, M., Lavidas, K., & Komis, V. (2023). The use of ChatGPT as a learning tool to improve foreign language writing in a multilingual and multicultural classroom. Advances in Mobile Learning Educational Research. https://doi.org/10.25082/amler.2023.02.009
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.