Rhetorical distinctions: Comparing metadiscourse in essays by ChatGPT and students

This study investigates the use of metadiscourse in argumentative essays generated by ChatGPT compared to those written by British university students. Using Hyland's (2005) framework, we analysed interactive and interactional metadiscourse to uncover rhetorical and linguistic distinctions. The...

Full description

Saved in:
Bibliographic Details
Published in:English for specific purposes (New York, N.Y.) Vol. 79; pp. 17 - 29
Main Authors: Jiang, Feng (Kevin), Hyland, Ken
Format: Journal Article
Language:English
Published: Elsevier Ltd 01.07.2025
Subjects:
Argumentative writing
ChatGPT
Interactional and interactive resources
Metadiscourse
Writing pedagogy
Interactional and interactive resources
Argumentative writing
ChatGPT
Metadiscourse
Writing pedagogy
ISSN:0889-4906
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This study investigates the use of metadiscourse in argumentative essays generated by ChatGPT compared to those written by British university students. Using Hyland's (2005) framework, we analysed interactive and interactional metadiscourse to uncover rhetorical and linguistic distinctions. The findings reveal that ChatGPT essays, though structurally coherent and logically organised, exhibit a significantly lower frequency of interactional metadiscourse, such as hedges, boosters, and attitude markers, leading to a more impersonal and expository tone. Conversely, student essays demonstrate higher rhetorical engagement, employing nuanced stance markers and personalised expressions to foster reader interaction. ChatGPT prioritises clarity and structural coherence through transitions and endophoric markers, reflecting its algorithmic nature and training. The variability in student writing highlights the influence of individual style and instructional practices. These differences underscore the complementary roles of AI and human authorship in academic writing, with implications for pedagogy. This research advances our understanding of the rhetorical strategies employed by large language models and their potential in academic contexts. •ChatGPT essays show fewer interactional metadiscourse, favouring structural clarity.•Student essays reveal greater rhetorical engagement and reader interaction.•ChatGPT prioritises transitions and coherence over nuanced audience engagement.•Student texts display diverse personal styles, reflecting instructional practices.•Findings underscore AI and human authors' complementary roles in writing.
ISSN:0889-4906
DOI:10.1016/j.esp.2025.03.001