cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Sukmawaty
Contact Email
sukmawaty@uinpalopo.ac.id
Phone
+6282346906030
Journal Mail Official
journals.pearl@gmail.com
Editorial Address
Jl. Makkarani Komp. Green Riyousa Blok E. No 12. A Gowa Sulawesi Selatan, Indonesia
Location
Unknown,
Unknown
INDONESIA
Pedagogical Education and Review of Linguistics
Published by South Sulawesi Education Development
ISSN : -     EISSN : 31234283     DOI : https://doi.org/10.58230/pearl
Core Subject : Education,
Languange, Linguistic, Communication & Media
PEARL endeavors to publish high-quality, original research articles, reviews, and case studies that address the challenges and opportunities presented when linguistic theory meets classroom practice. Our scope covers: The practical application of phonetics, syntax, semantics, and pragmatics in teaching. Innovations in teaching methodologies derived from linguistic research. Case studies showcasing successful integration of linguistics in language education. Reviews of instructional materials, tools, and technology grounded in linguistic principles.
Arjuna Subject : Umum - Umum
Articles 31 Documents
 1   2   3   4 
Deviasi Sintaksis dan Kalimat Mubazir pada Terjemahan Akademik Berbasis Generative AI: Studi Komparatif ChatGPT dan Gemini Muhammad Rifki Anggana
Pedagogical Education and Review of Linguistics Volume 2 Issue 3, September 2026
Publisher : South Sulawesi Education Development

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58230/dwsqzv59

Abstract

This study analyzes the academic translation performance of two generative artificial intelligence platforms, ChatGPT and Gemini, focusing on identifying syntactic deviations and redundant sentence constructions. While prior research has documented syntactic weaknesses in generative AI translation in general, systematic platform-to-platform comparisons on comparable academic corpora remain scarce. Employing a qualitative approach with a descriptive-comparative content analysis method, this research examines a corpus of 10 English international journal abstracts translated into Indonesian by both AIs. The results indicate that both platforms frequently produce translations with syntactic deviations, such as rigid sentence structures and literal translations that mimic source language patterns, as well as redundant sentence constructions in the form of pleonasm and semantic repetition, though with distinct dominant patterns, namely ChatGPT more frequently produces rigid, literal structures, while Gemini more frequently produces convoluted sentences and semantic redundancy. These limitations suggest that current generative AI is not yet fully capable of internalizing the stylistic nuances and pragmatics of Indonesian in an academic context. The pedagogical implications of these findings highlight the importance of developing platform-aware critical post-editing skills for students and adapting language learning curricula to train them in recognizing and correcting AI-generated errors. This study contributes to understanding the platform-specific strengths and weaknesses of generative AI in academic translation and suggests future directions for AI development.

Page 4 of 4 | Total Record : 31

 1   2   3   4 

Filter by Year

2025 2026


Reset
Filter By Issues
All Issue Volume 2 Issue 3, September 2026 Volume 2 Issue 2, May 2026 Volume 2 Issue 1, January 2026 Volume 1 Issue 3, September 2025 Volume 1 Issue 2, May 2025 Volume 1 Issue 1, January 2025