Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.51558/2303-4858.2025.13.2.159

Iterative refinement: Using the generative AI chatbot Copilot as a feedback tool – Evidence from the ELT classroom

Victoria Eibinger orcid id orcid.org/0009-0005-5432-155X ; University of Graz, Austria *
Hannes Fromm ; University of Graz, Austria
Margit Reitbauer ; University of Graz, Austria

* Dopisni autor.


Puni tekst: engleski pdf 610 Kb

str. 159-180

preuzimanja: 127

citiraj


Sažetak

Recent advances in artificial intelligence have opened the door to new applications in the teaching of writing. This article addresses a current research gap by combining automated AI-based feed-back, provided by Microsoft Copilot, with teacher feedback and student self-correction. The present study investigates the effectiveness of AI-assisted feedback on EFL students’ writing skills. Data were collected from 41 university students. The feedback from Copilot and the subsequent revisions made by students were analysed using MAXQDA according to categories such as genre conventions, accuracy, lexical scaffolding, and content. Results suggest that considerable improvements in writing skills, especially in the areas of lexical scaffolding and line of argumentation, can be achieved through AI-assisted feedback

Ključne riječi

AI chatbot; EFL writing instruction; AI-assisted feedback; AI-literacy

Hrčak ID:

343789

URI

https://hrcak.srce.hr/343789

Datum izdavanja:

25.1.2026.

Posjeta: 251 *