Assessing the accuracy of MT and AI tools in translating humanities or social sciences Arabic research titles into English: Evidence from Google Translate, Gemini, and ChatGPT

Abstract

Breakthroughs and advances in translation technology by virtue of AI-powered MT tools and techniques contributed significantly to providing near-perfect translation. This study aims to evaluate the accuracy of three translation technologies (Google Translate, Gemini, and ChatGPT) in translating multidisciplinary Arabic research titles in the Humanities and Social Sciences into English. A corpus of 163 titles of Arabic research articles from various disciplines, including media studies, literature, linguistics, education, and political science, was extracted from a Scopus-indexed journal, namely Dirasat: Human and Social Sciences Series. The research methodology in the present study lends itself largely to Koponen’s (2010) translation error strategy framework. Based on the data analysis, the findings showed that the renditions provided by these programs were categorically marked with either sense or syntax errors, which often rendered the translations inaccurate. Many polysemous terms with multiple related senses were mistranslated. The results showed that the Gemini translations contained the least errors. In contrast, the human translations contained the least mistranslation and diction errors. Google Translate and ChatGPT, on the other hand, contained the highest number of equivalence-based errors. Unexpectedly, the human translations contained the highest number of syntactic errors, reflecting a lack of target language proficiency. The study's conclusions and findings would be beneficial to translators, students, and scholars who may consider translating their Arabic study research titles and abstracts through the most commonly used AI tools.