Utilizing an AI-Based Grammar Checker in an EFL Writing Classroom
Abstract
This study explored the effectiveness of using feedback from Grammarly in EFL writing classrooms and students’ perceptions of such feedback. Writing assignments by 31 university students were examined regarding the numbers and types of feedback provided by the online writing support tool Grammarly and the students’ uptake of the feedback in their immediate revisions and subsequent writing. The results show that, of the five types of feedback provided by Grammarly, grammar appeared most frequently, followed by spelling, conciseness, punctuation, and conventions. Participants responded to the feedback approximately 75% of the time, but their response rates declined as they gained more experience in using the program, showing a tendency to evaluate the feedback before initiating corrections to their writing. Also, the analysis revealed that the instant and intensive feedback from Grammarly enhanced students’ awareness and accuracy in their use of determiners. Conversely, the students also used the program to reduce the cognitive load required to complete in-class writing tasks.
Integrity signals
Registry
Cites
Statistics
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?
There are legitimate uses of AI tools using LLMs in supporting the education of students.
“There are legitimate uses of these tools in supporting the education of students, meaning HEIs must carefully consider how policies dealing with student use of this software are created.”
From Academic Integrity considerations of AI Large Language Models in the post-pandemic era: ChatGPT and beyond (2023) · cites this paper as Park & Yang, 2020
Cited by
Sorted by citations
Perkins, M. (2023) · Journal of University Teaching and Learning Practice · doi:10.53761/1.20.02.07 · Cited by 839 · see citing works
- Authors
- Park, J.-H., & Yang, I. Y.
- Venue
- Korean Journal of Applied Linguistics
- Published
- 2020-03-31
- Volume
- 36
- Issue
- 1
- Pages
- 97-120
- ISSN
- 1225-3871
- Cited by
- 5
- References
- 0
- Language
- en
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
