Sentiment analysis is a core task in natural language processing, commonly used to detect opinions or emotions in text. While significant progress has been made for high-resource languages such as English and French, dialectal Arabic remains underexplored due to its informal writing style, limited annotated data, and complex morphology. Diacritics (tashkīl), which are rarely used in dialectal corpora, especially those collected from social media, are usually removed during preprocessing to reduce noise. In this study, we investigate the impact of automatically adding tashkīl on sentiment classification performance. We applied diacritization to datasets in Algerian Arabic, Moroccan Arabic, and Modern Standard Arabic (MSA), and trained several models including large language models (LLMs) and transformer-based models. We also evaluated two data augmentation techniques: Masked Language Modeling (MLM) and Last Vowel Deletion (LVD), both with and without tashkīl. Our results show an improvement of up to +4.9 percentage points in F1-score (LLaMA-2-7B, Algerian Arabic, from 0.4950 to 0.5440) for dialectal models when tashkīl is included, but a decrease for models trained only on MSA. For Algerian Arabic, combining diacritization with data augmentation increased the score by up to +8.2
Large Language Models (LLMs) have demonstrated remarkable effectiveness across a wide range of natural language processing (NLP) tasks, including machine translation. Nevertheless, existing research has predominantly focused on high-resource languages, leaving low-resource languages comparatively underexplored. In this paper, we introduce a reinforcement learning–free approach for improving Moroccan Arabic-to-English translation. Specifically, we propose Embedding-based Adaptive Rejection Preference Optimization (EARPO), which performs adaptive rejection at the semantic level using linear attention and leverages a triplet dataset constructed with the SMAUG framework to generate critical translation errors. Experimental results show that EARPO consistently outperforms the baseline Adaptive Rejection Preference Optimization (ARPO) across the evaluated models and metrics, surpasses Supervised Fine-tuning (SFT), and remains competitive with Contrastive Preference Optimization (CPO).
Depression remains one of the most prevalent mental health conditions worldwide, yet most automated detection systems focus on English text and overlook the multilingual, multimodal nature of social media communication. This limitation is particularly significant in India, where users frequently write using Hinglish and other Hindi variants, posing substantial challenges for standard language processing pipelines. This study introduces a time-aware multilingual multimodal framework for detecting depression-related expressions in social media posts collected from X (formerly Twitter). The model jointly learns from text, images, and posting time, enabling it to capture how users express themselves across languages and modalities. To support this work, we construct and annotate a dataset of 15,739 posts from 3,471 users covering four linguistic varieties: English, Roman Hindi, Devanagari Hindi, and Hinglish. The contributions of this work are twofold: it presents a multilingual multimodal dataset for Indian social media depression-related content detection, and it provides a systematic evaluation of encoding and fusion strategies, achieving an F1-score of 0.782 with cross-lingual transfer capability demonstrated on a Bengali corpus. All outputs are intended as a content-screening aid and do not constitute clinical diagnosis.
Large Language Models (LLMs) have demonstrated remarkable capabilities across various natural language processing tasks, yet their effectiveness for Arabic language processing remains underexplored. This paper presents an in-depth evaluation of instruction tuning for Arabic NLP tasks using three prominent LLMs: LLaMA 3.1-8B, AceGPT-v2-8B, and Qwen3-8B. To support this evaluation and future Arabic NLP research, we introduce STAR (inStruction Tuning for ARabic), a publicly released collection of 355 Jinja2 instruction templates spanning 87 datasets and 20 NLP tasks, together with over 46 million rendered instruction–output pairs. Using a 60-template subset of STAR, we evaluate three model variants for each LLM—base, instruction-tuned, and custom LoRA-tuned—on six diverse Arabic NLP tasks (MCQ-based Natural Language Understanding, Natural Language Inference, Dialect Identification, Sarcasm Detection, Machine Translation, and Summarization) across 12 datasets. We employ both intra-dataset evaluation (generalization within training distribution) and intra-task evaluation (generalization across datasets of the same task) to assess model robustness. Results demonstrate that instruction tuning consistently improves performance across most tasks, with notable variations in effectiveness across different tasks and prompts. Models show sensitivity to cross-dataset generalization and prompt styles, while task-specific tuning noticeably reduces prompt sensitivity. Our findings reveal that optimal results depend on careful prompt engineering and task-specific settings, providing insights for developing more effective Arabic language modeling practices. Our code is available at https://github.com/KFUPM-JRCAI/instructions-tuning .
This article presents the Russian Language-Monolingual corpus (RusLan-M, v.1.0), a longitudinal multimedia collection of early child speech from two Russian-speaking monolingual children: Tosya (ages 0;10–3;10, 246 recordings) and Yasha (ages 1;04–3;00, 42 recordings). The corpus consists of approximately 41 h (2,454 min.) of video recordings and 35,386 child utterances, available with transcriptions in the CHAT format on TalkBank. The corpus adheres to strict ethics requirements for data sharing with anonymization. We also conducted two exploratory investigations of the acquisition of Russian morphology using the mean length of utterance (MLU) and the newly developed Index of Productive Syntax for evaluating grammatical complexity in the nominal system of Russian (IPSyn-NP-R). These investigations illustrate how a comprehensive analysis of syntactic and morphological structures in Russian language development can be conducted and highlight the kinds of questions that can be answered using the RusLan-M data. The RusLan-M corpus represents an application of corpus linguistics methods to the Russian language and fills a significant gap in the limited data and resources available for Russian child language research.
