Jul 2026· JOIV: International Journal on Informatics Visualization· Vol 10, pp. 1538· 0 citations
TL;DR
The results demonstrate that linear discriminative models and appropriate lexical feature engineering can provide a very accurate and interpretable baseline for the development of natural language processing algorithms for Arabic.
Abstract
Classical Arabic narratives present unique challenges in the computational analysis of their texts, due to the language's highly complex morphology, orthographic ambiguity, and stylistic variations over time. This study presents a framework for Explainable Artificial Intelligence (XAI) for cognitive and pragmatic study of Arabic texts with two typical tasks, namely author attribution and Named Entity Recognition (NER). The ground truth used in the framework is not synthetically created, but rather comes from two already available resources, that are sufficiently rich to provide strong, machine-verifiable ground truth: the OpenITI corpus segmented in passages and labeled by the Author URI for multi-class attribution for six classical authors and CLEAN-ANERCorp, a corrected CoNLL format Arabic NER corpus recast as a windowed-context classification task with labels PER, LOC, ORG, MISC and O. The four traditional machine-learning classifiers, Logistic Regression, Multinomial Naive Bayes, Linear Support Vector Machine (SVM), and Random Forest are systematically benchmarked after the normalization and TF-IDF vectorization of the Arabic texts (unigrams and bigrams, vocabulary limited to approximately 8,000 features, minimum document frequency of 1). Models are tested using an 80/20 stratified train-test split, and accuracy, weighted precision, weighted recall, weighted F1-score, Matthews Correlation Coefficient (MCC), and Cohen's Kappa are used to evaluate models. The Linear SVM achieves the best performance with an 80/20 split, with an author-attribution F1 of 0.932 and an NER F1 of 0.809, while an 80/40 split yields an author-attribution F1 of 0.942. The ten most important TF-IDF features are extracted for each class and presented as a pair of Arabic-English word lists, thereby providing algorithmic transparency. Together, the results demonstrate that linear discriminative models and appropriate lexical feature engineering can provide a very accurate and interpretable baseline for the development of natural language processing algorithms for Arabic.
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
The article examines linguistic features of Ukrainian socio-political news texts generated by large language models and methods for their automated identification. The aim is to substantiate lexical, stylistic, compositional and semantic markers that may indicate AI-generated text and to outline a computational-linguistic detection framework. The study proposes combining philological interpretation with NLP procedures: preprocessing, lexical diversity assessment, clustering, vectorization and transformer-based classification. It is argued that automated detection should not replace expert linguistic analysis but should serve as an auxiliary tool for evaluating the probable origin of a text in media linguistics, fact-checking, and educational practic
N. Babkova, D. Huliieva, Z. Kochuieva et al.· Bulletin of the National Tec...· 0 citations
It was concluded that texts generated by artificial intelligence constitute a separate linguistic phenomenon with its own set of characteristics, which requires a special typology and a flexible, updatable analysis methodology.
L. Kravets, Viktória Stefuca, N. Libak et al.· Computer and Decision Making...· 0 citations
Arabic Speech Recognition (ASR) faces compounded challenges due to rich dialectal variation, morphological complexity, and data scarcity. While self-supervised speech models such as HuBERT excel in acoustic representation, they lack the deep linguistic reasoning needed to resolve ambiguities unique to Arabic. Large Language Models (LLMs) offer complementary grammatical and semantic knowledge, yet their role in systematic, real-time Arabic ASR error correction remains underexplored. In this work, we propose a novel two-stage framework for accurate and efficient Arabic ASR enhancement. First, we fine-tune a HuBERT model on the Common Voice Arabic corpus, establishing a baseline word error rate (WER) of 19.3%. Second, we introduce Distribution-Aware In-Context Learning (DA-ICL), a prompting strategy that supplies the Arabic LLM Aya-23-8B with a curated set of few-shot examples derived from a systematic taxonomy of ASR error types, including phonetic confusions and morpho-orthographic errors. DA-ICL enables precise, structurally faithful corrections, reducing WER to 9.6% without undesirable sentence rephrasing. To address domain shift and catastrophic forgetting, we further apply Low-Rank Adaptation (LoRA) to adapt a pre-trained HuBERT model to new domains parameter-efficiently. This approach reduces out-of-domain WER from 67% to 24% while preserving in-domain performance, demonstrating improved generalization without full fine-tuning. Our results confirm that combining HuBERT-based acoustic modeling with LLM-based DA-ICL correction and LoRA-efficient adaptation yields a robust, accurate, and scalable solution for Arabic ASR, effectively bridging the gap between acoustic signal and linguistic knowledge. Our framework achieves a WER of 9.6% on Common Voice Arabic, significantly outperforming Whisper-large (47.49% zero-shot, 37.89% with LoRA fine-tuning) and demonstrating the effectiveness of our linguistically-aware approach for Arabic speech recognition.
Rima Sbih, Assef Jafar, A. Kazem· IEEE Access· 0 citations
A narrative review compares contemporary Latin Natural Language Processing tools and their use cases for pedagogical applications and concludes that an integrated, multi-tool approach is most effective for supporting Latin pedagogy.
Aidan Han· American Journal of Student...· 0 citations
Semantic analysis has become a central challenge in natural language processing, driven by exponential growth in digitized textual data and the need for automated content processing across multiple applications including machine translation, text classification, sentiment analysis, and information retrieval. However, while semantic analysis methods are well-developed for resource-rich languages such as English, morphologically complex languages like Uzbek suffer from deficiencies in annotated corpora, lexical-semantic resources, and high-quality vector models – a gap amplified by governmental initiatives in digital economy development and national language technology advancement. This section grounds semantic analysis in the distributional semantics hypothesis principle that words exhibiting similar contexts possess similar meanings – thereby recasting the problem as a geometric challenge within continuous vector spaces. Two principal mathematical strategies are formalized: (1) prediction-based models (word2vec: CBOW/Skip-gram), which optimize context prediction objectives, and (2) count-based models (GloVe), which leverage global co-occurrence statistics through matrix factorization. Both project high-dimensional word co-occurrence relationships into low-dimensional dense vector spaces, enabling semantic analogy representation. For resource-scarce languages like Uzbek, cross-lingual embedding alignment (Procrustes optimization) enables semantic knowledge transfer from resource-rich languages, facilitating shared semantic spaces across the Turkic language family. The section concludes with formal problem specification: given vocabulary V and corpus C, semantic analysis is formalized as (1) a mapping problem preserving distributional properties, (2) an optimization problem minimizing loss through gradient-based methods, and (3) an evaluation problem assessing quality through semantic similarity, analogy, and downstream NLP task performance.
D. Akhmedjanova· Международный Журнал Теорети...· 0 citations