Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Ukazh: Journal of Arabic Studies
Muhammad Hilman
Institut Agama Islam Imam Syafii Pekanbaru, Indonesia
Religion Humanities Education Social Sciences Other

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisis Akurasi I‘rab Struktur Kalimat Bahasa Arab pada Output Artificial Intelligence ChatGPT: Studi Mixed Methods Muhammad Hilman; Muhammad Azhar
Ukazh : Journal of Arabic Studies Vol. 7 No. 2 (2026): Ukazh : Journal of Arabic Studies, June 2026
Publisher : Institut Muslim Cendekia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37274/ukazh.v7i2.251

Abstract

The increasing use of ChatGPT as a source for learning Arabic requires a critical evaluation of the accuracy of the grammatical analysis it produces. This study aims to analyze the accuracy and precision of i‘rab in Arabic sentences generated by ChatGPT. This research employed a mixed methods approach with a sequential exploratory design. The data consisted of 12 sentences with variations in syntactic structure, collected purposively and analyzed through content analysis. The qualitative analysis revealed errors in complex structures, such as al-bina’ lil-majhul, multi-maf‘ul, uslub syarṭ, istifham, as well as taqdim–ta’khir and i‘rab taqdir. The errors also included incorrect identification of fa’il, inaccuracies in i‘rab markers, and inconsistencies in wording. The quantitative results showed an accuracy rate of 46.81% (44/94), indicating that ChatGPT is fairly capable of recognizing basic nahwu patterns. However, these findings indicate that the use of ChatGPT at the basic level may actually risk instilling conceptual errors. Therefore, ChatGPT cannot replace classical nahwu references and must be used critically and verified with authoritative sources.
Co-Authors Muhammad Azhar