Integrating AI into Arabic Linguistics: A Methodological Framework for Reproducible and Interpretable 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.