A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles

AI advancements have made ChatGPT a remarkable and versatile tool in education and linguistics, showcasing its potential to mimic human conversation and comprehend language. Scholars are intrigued by ChatGPT’s text data handling, yet its application in rhetorical move analysis remains largely unexpl...

Full description

Bibliographic Details
Main Authors: Geng, Hui, Nimehchisalem, Vahid, Zargar, Mohsen, Mukundan, Jayakaran
Format: Article
Language:English
Published: Ideas Spread 2024
Online Access:http://psasir.upm.edu.my/id/eprint/116382/
http://psasir.upm.edu.my/id/eprint/116382/1/116382.pdf
_version_ 1848866990582661120
author Geng, Hui
Nimehchisalem, Vahid
Zargar, Mohsen
Mukundan, Jayakaran
author_facet Geng, Hui
Nimehchisalem, Vahid
Zargar, Mohsen
Mukundan, Jayakaran
author_sort Geng, Hui
building UPM Institutional Repository
collection Online Access
description AI advancements have made ChatGPT a remarkable and versatile tool in education and linguistics, showcasing its potential to mimic human conversation and comprehend language. Scholars are intrigued by ChatGPT’s text data handling, yet its application in rhetorical move analysis remains largely unexplored. Therefore, the objective of this study is to investigate the ability of GPT-4 in the identification of rhetorical moves employed in the abstracts of tourism research articles indexed in Scopus. The essentiality of moves was also reported. Additionally, this research seeks to compare the accuracy of GPT-4’s analysis with that of humans. Adopting Hyland’s (2000) fivemove model, the results indicated that GPT-4 analyzes moves more quickly but less accurately than human experts, and the four principal types of errors committed by GPT-4 include redundancy/over-count, unmatched categorization, incorrect sequence, and vague identification. The findings also revealed that Move 2 (Purpose) and Move 4 (Findings) are obligatory with a 100% essentiality rate through both GPT-4 and human analysis. Differences arise in certain steps of Move 1 (Introduction), Move 3 (Methods), and Move 5 (Conclusion), where GPT-4 often sees higher essentiality rates. This study shed light on the testament to AI’s current capabilities in move analysis in academic discourse.
first_indexed 2025-11-15T14:29:23Z
format Article
id upm-116382
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T14:29:23Z
publishDate 2024
publisher Ideas Spread
recordtype eprints
repository_type Digital Repository
spelling upm-1163822025-03-27T06:38:57Z http://psasir.upm.edu.my/id/eprint/116382/ A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles Geng, Hui Nimehchisalem, Vahid Zargar, Mohsen Mukundan, Jayakaran AI advancements have made ChatGPT a remarkable and versatile tool in education and linguistics, showcasing its potential to mimic human conversation and comprehend language. Scholars are intrigued by ChatGPT’s text data handling, yet its application in rhetorical move analysis remains largely unexplored. Therefore, the objective of this study is to investigate the ability of GPT-4 in the identification of rhetorical moves employed in the abstracts of tourism research articles indexed in Scopus. The essentiality of moves was also reported. Additionally, this research seeks to compare the accuracy of GPT-4’s analysis with that of humans. Adopting Hyland’s (2000) fivemove model, the results indicated that GPT-4 analyzes moves more quickly but less accurately than human experts, and the four principal types of errors committed by GPT-4 include redundancy/over-count, unmatched categorization, incorrect sequence, and vague identification. The findings also revealed that Move 2 (Purpose) and Move 4 (Findings) are obligatory with a 100% essentiality rate through both GPT-4 and human analysis. Differences arise in certain steps of Move 1 (Introduction), Move 3 (Methods), and Move 5 (Conclusion), where GPT-4 often sees higher essentiality rates. This study shed light on the testament to AI’s current capabilities in move analysis in academic discourse. Ideas Spread 2024-06-05 Article PeerReviewed text en cc_by_4 http://psasir.upm.edu.my/id/eprint/116382/1/116382.pdf Geng, Hui and Nimehchisalem, Vahid and Zargar, Mohsen and Mukundan, Jayakaran (2024) A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles. International Linguistics Research, 7 (2). pp. 1-12. ISSN 2576-2974; eISSN: 2576-2982 https://j.ideasspread.org/index.php/ilr/article/view/1290 10.30560/ilr.v7n2p1
spellingShingle Geng, Hui
Nimehchisalem, Vahid
Zargar, Mohsen
Mukundan, Jayakaran
A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles
title A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles
title_full A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles
title_fullStr A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles
title_full_unstemmed A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles
title_short A comparison of rhetorical move analysis by GPT-4 and humans in abstracts of scopus-indexed tourism research articles
title_sort comparison of rhetorical move analysis by gpt-4 and humans in abstracts of scopus-indexed tourism research articles
url http://psasir.upm.edu.my/id/eprint/116382/
http://psasir.upm.edu.my/id/eprint/116382/
http://psasir.upm.edu.my/id/eprint/116382/
http://psasir.upm.edu.my/id/eprint/116382/1/116382.pdf