Jun 2026· Al-Ta'rib : Jurnal Ilmiah Program Studi Pendidikan Bahasa Arab UIN Palangka Raya· Vol 14, pp. 235-260· 0 citations
TL;DR
A comprehensive methodological framework encompassing linguistic problem formulation, resource selection and documentation, modeling and adaptation, evaluation and interpretation, and transparent reporting is proposed that bridges computational innovation with linguistic theory and provides practical guidance for conducting robust AI-assisted Arabic linguistic research.
Abstract
The rapid advancement of Artificial Intelligence (AI) has transformed Arabic linguistic research by enabling increasingly sophisticated Natural Language Processing (NLP) applications. However, methodological inconsistencies related to reproducibility, interpretability, dialectal diversity, and resource documentation continue to limit the scientific validity of AI-based Arabic linguistic studies. This study aims to synthesize recent developments in AI-assisted Arabic linguistics and propose a comprehensive methodological framework that promotes transparent, reproducible, and linguistically accountable research. Using a Systematic Literature Review (SLR) approach, relevant publications were critically analyzed to identify emerging trends, methodological challenges, and best practices in Arabic NLP. The findings reveal a paradigm shift from model-centric innovation toward methodology-centered research, highlighting the growing importance of dialect-aware evaluation, domain-specific resources, explainable AI, efficient adaptation strategies, and rigorous reporting standards. Based on these synthesized findings, the study proposes a five-stage methodological framework encompassing linguistic problem formulation, resource selection and documentation, modeling and adaptation, evaluation and interpretation, and transparent reporting. The framework bridges computational innovation with linguistic theory and provides practical guidance for conducting robust AI-assisted Arabic linguistic research. By emphasizing reproducibility, interpretability, and linguistic accountability, this study contributes a principled foundation for future Arabic NLP research and supports the development of more reliable, equitable, and scientifically rigorous language technologies.
Machine translation has become more fluent and contextually accurate with recent advances in artificial intelligence. However, terminological consistency has been underexplored, particularly in political and electoral discourse where lexical repetition and conceptual precision are critical for cohesion and clarity. This study investigates terminological consistency in AI-generated English–Arabic political translations produced by ChatGPT and Google Gemini Advanced. The translations were generated and analyzed between January and June 2026 using the systems’ default settings to ensure comparability and avoid potential variations resulting from user-configured parameters. The study employs a mixed-methods corpus-based approach. The study analyzes 30 political and electoral texts with 60 recurring key terms. Quantitative analysis measures the degree of consistency in the form of stability percentages, and qualitative analysis studies lexical variation and its effect on discourse cohesion and clarity. The adequacy and consistency of the translation were checked against a reference translation based on the United Nations Development Programme (UNDP) Arabic Lexicon of Electoral Terminology. The results indicate that ChatGPT achieved higher terminological consistency than Google Gemini. ChatGPT’s lexical equivalents for repeated political and electoral terms were more stable than its Gemini counterpart, which showed more lexical variation, especially in context-sensitive terms such as campaign, electoral law, and judicial review. The study concludes that terminological consistency should be considered as a separate dimension of translation quality and emphasizes the importance of terminology control and human post-editing in AI-assisted political translation
Osama Bala· (Faculty of Arts Journal) مج...· 0 citations
Generative artificial intelligence is increasingly used in Arabic language education, yet its performance in understanding and processing Arabic grammar remains markedly inconsistent. This narrative review examines why AI systems struggle with Arabic grammar and explores the pedagogical implications of these computational limitations. Drawing on 26 primary studies published between 2020 and 2026, the review identifies five interconnected linguistic challenges: the non-linear root-and-pattern morphology of Arabic, the routine omission of diacritics that obscures grammatical case, extensive dialectal diversity, persistent data scarcity, and the syntactic complexity of the i'rab case system. Empirical evidence shows that even advanced models perform substantially worse on morphological and syntactic tasks than on surface-level tasks, with GPT-4o achieving only 67 percent accuracy on Arabic grammar benchmarks and Arabic-specific models scoring considerably lower. The review demonstrates that the structural features of Arabic that make natural language processing difficult are precisely the features that pose risks for learners who depend on AI without critical oversight. These risks include the formation of misconceptions, overreliance on AI-generated outputs, and the erosion of critical thinking and teacher expertise. The findings suggest that effective AI integration in Arabic grammar instruction requires a Human-in-the-Loop approach, targeted teacher training, and the development of critical AI literacy among learners
Muhammad Fariq Heemal Attruk, N. Mustapha· EDUCATUM: Scientific Journal...· 0 citations
Poetry is a unique form of expression valued for its role in preserving cultural heritage. Analyzing Arabic poetry is time-consuming and requires a high level of linguistic expertise; therefore, computational methods are useful, as they enable large-scale, extensive, and systematic analysis of poetry, thereby improving its accessibility for researchers and students. This article presents the first systematic review of natural language processing (NLP) and machine learning (ML) approaches for Arabic poetry. It addresses the question of which research tasks, methodologies, datasets, and evaluation approaches have been applied to Arabic poetry, and which trends and research gaps can be identified in the existing literature. In accordance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), the author conducted an exhaustive search across six major academic databases (ACL Anthology, IEEE Xplore, ACM, SpringerLink, Science Direct, and Google Scholar) for relevant studies published between January 2010 and May 2025. Eligibility was evaluated in several phases, and re-examination was conducted to ensure accuracy. The author performed task-level categorization, extracted key characteristics from each study, synthesized the findings, and presented them in tables and figures to highlight the main trends and research gaps in the literature. This study presents the first structured task-level synthesis of the field, identifying methodological trends, detecting evaluation inconsistencies, and highlighting research gaps that have not been critically consolidated before. Furthermore, the author assembled a comprehensive collection of available datasets and resources to promote standardized assessment.
Backround - The rapid advancement of Artificial Intelligence (AI) in translation studies has transformed how literary texts are processed, shifting from literal word-for-word transfer to more contextually nuanced approaches. Literary fables demand particular sensitivity to personification, onomatopoeia, and moral messaging.
Urgency of Research - Despite the proliferation of AI translation tools, previous studies have predominantly focused on macro-level quality evaluation (e.g., fluency and accuracy) rather than examining the micro-linguistic strategies AI employs. There remains a significant gap in understanding how different AI models identify and apply established translation techniques within Molina and Albir's comprehensive framework of 18 translation techniques.
Research Objectives - This study aims to evaluate and compare the performance of four AI tools—ChatGPT, Gemini, Claude, and DeepL—in identifying and applying translation techniques in the literary fable "The Clever Rabbit," specifically examining how each model utilizes Molina and Albir's 18 translation techniques to achieve dynamic equivalence.
Research Method - Adopting a qualitative descriptive approach, this study employs purposive sampling to select translation units demonstrating specific techniques. Data were collected through comparative textual analysis of one English source text and four Indonesian target texts, validated through theoretical triangulation and source triangulation.
Research Findings - The findings reveal a clear strategic polarization: generative AI models (ChatGPT, Gemini, Claude) demonstrate dominance in complex transformation techniques such as Modulation (20-23%), Equivalence (12-13%), and Explicitation, reflecting deeper contextual understanding. In contrast, DeepL shows extreme reliance on Literal Translation (>65%) with minimal cultural or stylistic adaptation. ChatGPT excels in local adaptation through generalization and particularization; Gemini stands out in narrative vitality through expressive lexical variation; and Claude offers structural efficiency through precise grammatical reduction.
Research Conclusion & Novelty - This study concludes that while all AI tools can transfer denotative meaning, generative models (LLMs) are superior in applying high-level translation techniques necessary for maintaining emotional nuance, discourse cohesion, and literary appeal. The novelty lies in its micro-linguistic analysis using Molina and Albir's comprehensive taxonomy across four distinct AI platforms, providing unprecedented insight into the "black box" of AI translation strategies. The findings offer practical guidance for educators, researchers, and translators in selecting appropriate AI tools, emphasizing that critical human post-editing remains indispensable for achieving true literary equivalence.
This essay aimed to critically examine the widely held claim in contemporary Arabic linguistic research that European structuralism decisively transformed the study of Arabic grammar. To this end, a qualitative, analytical, and historical-comparative approach was adopted, based on a critical analysis of primary sources of European structuralism—primarily the works of Ferdinand de Saussure, Leonard Bloomfield, and Roman Jakobson—as well as the classical and modern Arabic grammatical tradition, represented by Sibawayh's Al-Kitāb and Tammam Hassan's work on the theory of convergence of clues (taḍāfur al-qarāʾin). The analysis was supplemented by recent scholarly literature on Arabic linguistics, structuralism, functionalism, and cognitive linguistics. The results showed that structuralism's main contribution lay not in offering new knowledge about the Arabic language, but in introducing a different epistemological criterion for evaluating the validity of linguistic explanations. This approach allowed for the identification of limitations in the classical theory of ʿāmil, although Hassan's alternative proposal also failed to conclusively resolve these difficulties when subjected to the same level of critical analysis. It is concluded that the influence of structuralism on Arabic grammar has been more methodological than theoretical, and that much of the existing literature consists of pedagogical reinterpretations rather than empirically verified developments
Translating the Qurʾān from Classical Arabic into Malay presents profound linguistic, cultural, and theological challenges. Classical Arabic’s intricate morphology, polysemy, and rhetorical structures often lack direct Malay equivalents, while culturally specific metaphors and symbolic expressions risk semantic distortion when rendered literally. While previous studies have largely neglected the theological implications of rendering
mutashābihāt
(ambiguous) verses, as well as the linguistic, idiomatic, and figurative challenges involved, this study addresses that gap by examining a range of representative terms that pose linguistic, idiomatic, figurative, cultural, and theological challenges. Employing a qualitative semantic-thematic methodology grounded in classical
tafsīr
(exegesis) by authorities like al-Zamakhsharī and al-Rāzī, the research analyzes specific Malay translations, including the official
Terjemahan Al-Qurʾān Bahasa Melayu
. The verses subjected to case study were selected purposively according to two criteria: (a) the presence of polysemous
mutashābihāt
with significant theological or symbolic weight, and (b) terms that illustrate distinct types of translation challenges (linguistic, idiomatic, figurative, cultural, theological). The analysis reveals that structural disparities – like Arabic’s inflectional morphology versus Malay’s analytic structure – and literal renderings of idiomatic expressions frequently fail to preserve the Qurʾān’s theological coherence. In contrast, interpretive strategies rooted in
tafsīr
and semantic adaptation offer more accurate, culturally meaningful alternatives. The study concludes that an integrated exegetical-linguistic approach is essential for preserving the Qurʾān’s holistic meaning and theological integrity, demonstrating how this method resolves the tension between textual fidelity and accessibility for Malay-speaking audiences.
Huseyin Halil· Al-Bayan Journal of Qur an a...· 0 citations