ChatGPT translation vs. human translation: an examination of a literary text

This study evaluates the proficiency of ChatGPT-based translation compared to Human Translation (HT) using an Arabic literary work. It also examines potential translation gaps in ChatGPT and explores its potential to replace human translators. The research analyzes 12 excerpts from Mawsim Al-Hijra E...

Full description

Saved in:
Bibliographic Details
Main Authors: Rafat Al Rousan, Raghad Jaradat, Mona Malkawi
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Cogent Social Sciences
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/23311886.2025.2472916
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850139674854555648
author Rafat Al Rousan
Raghad Jaradat
Mona Malkawi
author_facet Rafat Al Rousan
Raghad Jaradat
Mona Malkawi
author_sort Rafat Al Rousan
collection DOAJ
description This study evaluates the proficiency of ChatGPT-based translation compared to Human Translation (HT) using an Arabic literary work. It also examines potential translation gaps in ChatGPT and explores its potential to replace human translators. The research analyzes 12 excerpts from Mawsim Al-Hijra Ela Al-Shamal (1966) by Tayeb Salih, comparing the English translation by Denys Johnson-Davies (Season of Migration to the North, 1969) with ChatGPT’s output. A mixed-method approach (qualitative and quantitative) was used, assessing translations through three dimensions of the Multidimensional Quality Metrics (MQM) framework: accuracy, fluency, and design. The MQM scoring model was also employed to ensure reliability. The findings show that HT is more accurate, with an average accuracy score of 94.5%, compared to 77.9% for ChatGPT. However, ChatGPT produces fluent translations, scoring 97.2% in fluency versus 96.6% for HT. Despite its fluency, ChatGPT struggles with design-related elements and often introduces superfluous content. The study concludes that ChatGPT is not a fully reliable tool for translating Arabic literature, which requires professional human translators like Denys Johnson-Davies to ensure accuracy and cultural sensitivity.
format Article
id doaj-art-92bbdf42d3af4e0b9e559fa24c51182d
institution OA Journals
issn 2331-1886
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Cogent Social Sciences
spelling doaj-art-92bbdf42d3af4e0b9e559fa24c51182d2025-08-20T02:30:10ZengTaylor & Francis GroupCogent Social Sciences2331-18862025-12-0111110.1080/23311886.2025.2472916ChatGPT translation vs. human translation: an examination of a literary textRafat Al Rousan0Raghad Jaradat1Mona Malkawi2Department of Translation, Yarmouk University, Irbid, JordanDepartment of Translation, Yarmouk University, Irbid, JordanDepartment of Translation, Yarmouk University, Irbid, JordanThis study evaluates the proficiency of ChatGPT-based translation compared to Human Translation (HT) using an Arabic literary work. It also examines potential translation gaps in ChatGPT and explores its potential to replace human translators. The research analyzes 12 excerpts from Mawsim Al-Hijra Ela Al-Shamal (1966) by Tayeb Salih, comparing the English translation by Denys Johnson-Davies (Season of Migration to the North, 1969) with ChatGPT’s output. A mixed-method approach (qualitative and quantitative) was used, assessing translations through three dimensions of the Multidimensional Quality Metrics (MQM) framework: accuracy, fluency, and design. The MQM scoring model was also employed to ensure reliability. The findings show that HT is more accurate, with an average accuracy score of 94.5%, compared to 77.9% for ChatGPT. However, ChatGPT produces fluent translations, scoring 97.2% in fluency versus 96.6% for HT. Despite its fluency, ChatGPT struggles with design-related elements and often introduces superfluous content. The study concludes that ChatGPT is not a fully reliable tool for translating Arabic literature, which requires professional human translators like Denys Johnson-Davies to ensure accuracy and cultural sensitivity.https://www.tandfonline.com/doi/10.1080/23311886.2025.2472916ChatGPThuman translationmultidimensional quality metricsliterary translationArtificial IntelligenceTranslation & Interpretation
spellingShingle Rafat Al Rousan
Raghad Jaradat
Mona Malkawi
ChatGPT translation vs. human translation: an examination of a literary text
Cogent Social Sciences
ChatGPT
human translation
multidimensional quality metrics
literary translation
Artificial Intelligence
Translation & Interpretation
title ChatGPT translation vs. human translation: an examination of a literary text
title_full ChatGPT translation vs. human translation: an examination of a literary text
title_fullStr ChatGPT translation vs. human translation: an examination of a literary text
title_full_unstemmed ChatGPT translation vs. human translation: an examination of a literary text
title_short ChatGPT translation vs. human translation: an examination of a literary text
title_sort chatgpt translation vs human translation an examination of a literary text
topic ChatGPT
human translation
multidimensional quality metrics
literary translation
Artificial Intelligence
Translation & Interpretation
url https://www.tandfonline.com/doi/10.1080/23311886.2025.2472916
work_keys_str_mv AT rafatalrousan chatgpttranslationvshumantranslationanexaminationofaliterarytext
AT raghadjaradat chatgpttranslationvshumantranslationanexaminationofaliterarytext
AT monamalkawi chatgpttranslationvshumantranslationanexaminationofaliterarytext