--- title: "Wajdi Zaghouani — papers, page 3 — Elamur Research" description: "Wajdi Zaghouani, Northwestern University in Qatar: 69 papers on Elamur Research (2010–2026), h-index 25 — affiliations, topics, co-authors…" canonical: "https://research.elamur.ai/free/en/authors/wajdi-zaghouani/page/3/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/wajdi-zaghouani/page/3/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Wajdi Zaghouani](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) / page 3 # Wajdi Zaghouani · page 3 69 papers in our library · 2010–2026 · page 3 of 3 [The profile, affiliations and co-authors →](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) ## Papers The most cited first (OpenAlex and our library). [← prev](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/2/) [1](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) [2](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/2/) **3** 51. **[AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-albanianllmsafety-safety-evaluation-dataset-large/)** *(2026 · 1 citation)* LLM safety benchmarks are concentrated on English and a few other well-resourced languages. Albanian, an isolated Indo-European branch with roughly 7.5 million speakers, has had essentially no dedicated safety resources. Multilingual suites either skip it or rely on machine-translated English prompts that miss local… 52. **[ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-arabicdialectsafety-dialect-aware-benchmark-arabic/)** *(2026 · 1 citation)* Arabic safety filters are usually built and tested on Modern Standard Arabic. Harmful requests phrased in regional dialects can therefore slip past them. Earlier Arabic safety resources either ignore dialects, mix them without labels, or are too small to evaluate each dialect separately. 53. **[Audience Engagement with Arabic Women's Social Empowerment and Wellbeing: A Decadal Corpus](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-audience-engagement-arabic-women-s/)** *(2026 · 1 citation)* Arabic NLP has many sentiment and emotion datasets, but most label the feeling expressed in the text itself. 54. **[Cohesion-6K: An Arabic Dataset for Analyzing Social Cohesion and Conflict in Online Discourse](https://md.research.elamur.ai/free/en/papers/athba-2026-cohesion-6k-arabic-dataset-analyzing/)** *(2026 · 1 citation)* Most computational work on polarized online talk detects overt toxicity. It rarely captures the subtler balance between divisive and unifying narratives. This paper addresses that gap for Arabic with Cohesion-6K, a collection of 6,000 public Facebook posts about the Israeli Occupation of Palestine, gathered through… 55. **[Enhancing Arabic Dialectal Sentiment Analysis through Advanced Data Augmentation Techniques](https://md.research.elamur.ai/free/en/papers/biswas-2025-enhancing-arabic-dialectal-sentiment-analysis/)** *(2025 · 1 citation)* The paper tackles sentiment classification of hotel and tourism reviews written in Arabic dialects. Training data for this setting is very scarce. The authors took part in the Ahasis shared task, which supplies only 860 labelled training sentences split evenly between Moroccan Darija and Saudi Arabic. To enlarge this… 56. **[MarsadLab at AraGenEval Shared Task: LLM-Based Approaches to Arabic Authorship Style Transfer and Identification](https://md.research.elamur.ai/free/en/papers/biswas-2025-marsadlab-arageneval-shared-task-llm/)** *(2025 · 1 citation)* The paper describes the MarsadLab entry to the AraGenEval shared task at ArabicNLP 2025. The task has two parts: rewriting a Modern Standard Arabic passage so it reads like a particular author while keeping its meaning, and recognising which of 21 authors wrote a given excerpt. The authors note that Arabic work in… 57. **[MarsadLab at AraHealthQA: Hybrid Contextual–Lexical Fusion with AraBERT for Question and Answer Categorization](https://md.research.elamur.ai/free/en/papers/bessghaier-2025-marsadlab-arahealthqa-hybrid-contextual-lexical/)** *(2025 · 1 citation)* This paper describes the MarsadLab entry for Track 1 (MentalQA) of the AraHealthQA 2025 Shared Task. The track has two multi-label problems on Arabic mental-health text. Subtask A assigns questions to topical categories, such as Diagnosis, Treatment or Epidemiology, plus a default "Other" class. Subtask B labels… 58. **[MarsadLab at BAREC Shared Task 2025: Strict-Track Readability Prediction with Specialized AraBERT Models on BAREC](https://md.research.elamur.ai/free/en/papers/ibrahim-2025-marsadlab-barec-shared-task-2025/)** *(2025 · 1 citation)* This paper describes a system for the BAREC 2025 Arabic readability shared task. The task is to assign one of 19 ordered difficulty levels to sentences and documents. The team entered only the Strict track, where training may use only the official splits. That restriction means little data, skewed classes and… 59. **[MarsadLab at PalmX Shared Task: An LLM Benchmark for Arabic Culture and Islamic Civilization](https://md.research.elamur.ai/free/en/papers/biswas-2025-marsadlab-palmx-shared-task-llm/)** *(2025 · 1 citation)* The paper describes a MarsadLab entry to PalmX 2025, a shared task that tests how well LLMs handle Arabic cultural and Islamic knowledge through four-option multiple-choice questions in Modern Standard Arabic. 60. **[MarsadLab at TAQEEM 2025: Prompt-Aware Lexicon-Enhanced Transformer for Arabic Automated Essay Scoring](https://md.research.elamur.ai/free/en/papers/bessghaier-2025-marsadlab-taqeem-2025-prompt-aware/)** *(2025 · 1 citation)* This paper describes MarsadLab's entry to TAQEEM 2025 Shared Task A. The task is to predict a holistic score (0–32) for student essays in Modern Standard Arabic, and evaluation uses prompts that do not appear in training (cross-prompt). The training data is small: 425 essays answering one explanatory and one… 61. **[MemeMind at ArAIEval Shared Task: Spotting Persuasive Spans in Arabic Text with Persuasion Techniques Identification](https://md.research.elamur.ai/free/en/papers/biswas-2024-mememind-araieval-shared-task-spotting/)** *(2024 · 1 citation)* The authors tackle ArAIEval 2024 Task 1, which asks systems to find which stretches of Arabic tweets and news paragraphs use persuasion or propaganda techniques and to name the technique for each stretch. 62. **[Narrative Navigators at FIGNEWS 2024 Shared Task: New Frontiers in Bias and Propaganda Annotation Techniques](https://md.research.elamur.ai/free/en/papers/alemadi-2024-narrative-navigators-fignews-2024-shared/)** *(2024 · 1 citation)* The paper describes how the team Narrative Navigators took part in the FIGNEWS 2024 Shared Task, which asked participants to manually label bias and propaganda in multilingual news posts about the 2023–2024 Israel-Palestine war. 63. **[A Multi-Task Learning Framework for Modeling Engagement and Topic-Sensitive Responses in Arabic Women's Discourse](https://md.research.elamur.ai/free/en/papers/bessghaier-2026-multi-task-learning-framework-modeling/)** *(2026)* The paper predicts how Facebook audiences collectively respond to Arabic posts about women's issues. It treats this as different from classic sentiment analysis, because readers' reactions often do not match the tone the author wrote in. The authors assembled roughly 158k public Arabic Facebook posts from 2014 to… 64. **[ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-arabdiscrim-decade-long-arabic-facebook/)** *(2026)* Arabic datasets on hate speech and discrimination have been built almost entirely from Twitter. Facebook has been neglected, even though it reaches several times more users in the MENA region and exposes richer engagement data. ArabDiscrim addresses this gap with 293,056 public Arabic posts from Facebook pages… 65. **[ArGuard Shared Task: Harmful Content Detection in Arabic Memes and LLM Prompts](https://md.research.elamur.ai/free/en/papers/alam-2026-arguard-shared-task-harmful-content/)** *(2026)* ArGuard is a 2026 shared task on detecting harmful Arabic content in two settings that earlier work treated separately: multimodal memes and prompts sent to LLMs. 66. **[ArPoMeme: An Annotated Arabic Multimodal Dataset for Political Ideology and Polarization](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-arpomeme-annotated-arabic-multimodal-dataset/)** *(2026)* Arabic political memes are a major channel for ideological expression online. Existing Arabic meme resources, however, concentrate on propaganda and hate, so the spread of ideologies across memes has not been mapped. ArPoMeme fills this gap with about 7,300 political memes collected from public Facebook pages and… 67. **[ClimateChat-300K: A Multi-Modal Facebook Dataset for Understanding Diverse Perspectives in Climate Communication](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-climatechat-300k-multi-modal-facebook/)** *(2026)* Studies of online climate discourse focus heavily on Twitter, partly because privacy rules and API limits make Facebook data hard to obtain. 68. **[JobArabi: An Arabic Corpus and Analysis of Job Announcements from Social Media](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-jobarabi-arabic-corpus-analysis-job/)** *(2026)* Arabic NLP lacks large, domain-specific resources on recruitment language, even though social media has become a major hiring channel across the MENA region. 69. **[Toward Cognitive Alignment in Large Language Models: Integrating Linguistic Theory and Human Data](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-cognitive-alignment-large-language-models/)** *(2026)* This position paper (CMCL 2026 at LREC) addresses a conceptual gap. LLMs predict human reading times and brain responses well, but that fit alone does not show they process language as people do. The author releases no new dataset or model. Instead, he proposes a framework of "cognitive alignment," adapted from… [← prev](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/2/) [1](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) [2](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/2/) **3**