--- title: "Wajdi Zaghouani — papers, page 2 — 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/2/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/wajdi-zaghouani/page/2/) [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 2 # Wajdi Zaghouani · page 2 69 papers in our library · 2010–2026 · page 2 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/) [1](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) **2** [3](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/3/) 26. **[MARASTA: A Multi-dialectal Arabic Cross-domain Stance Corpus](https://md.research.elamur.ai/free/en/papers/charfi-2024-marasta-multi-dialectal-arabic-cross/)** *(2024 · 13 citations)* MARASTA is a new Arabic stance-detection dataset. It addresses a gap in earlier Arabic stance resources, which tend to cover one topic or one country, or have badly skewed label distributions. The authors collected 4,657 sentences from four dialect regions: Maghreb (Tunisia), Egypt, the Levant (Palestine and Jordan)… 27. **[Guidelines and Annotation Framework for Arabic Author Profiling](https://md.research.elamur.ai/free/en/papers/zaghouani-2018-guidelines-annotation-framework-arabic-author/)** *(2018 · 13 citations)* Author profiling means inferring traits such as age, gender, dialect or native language from a person's writing. 28. **[MADARi: A Web Interface for Joint Arabic Morphological Annotation and Spelling Correction](https://md.research.elamur.ai/free/en/papers/obeid-2018-madari-web-interface-joint-arabic/)** *(2018 · 13 citations)* MADARi is a web-based tool for annotating social-media Arabic, which is heavily dialectal and full of spelling errors. 29. **[MemeMind at ArAIEval Shared Task: Generative Augmentation and Feature Fusion for Multimodal Propaganda Detection in Arabic Memes through Advanced Language and Vision Models](https://md.research.elamur.ai/free/en/papers/shah-2024-mememind-araieval-shared-task-generative/)** *(2024 · 12 citations)* The paper describes the MemeMind team's system for ArAIEval 2024 Task 2. The task asks whether Arabic memes are propagandistic, judged three ways: from the meme text alone (2A), from the image alone (2B), and from both together (2C). The training data is skewed toward non-propaganda, and the team's main response is… 30. **[DTW at Qur'an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain](https://md.research.elamur.ai/free/en/papers/premasiri-2022-dtw-qur-qa-2022-utilising/)** *(2022 · 11 citations)* The paper describes the DTW team's entry to the Qur'an QA 2022 shared task. The task is extractive (span-prediction) reading comprehension over Qur'anic passages, a domain with very little annotated data. The organisers supplied QRCD, which has 1,093 question–passage pairs and 1,337 question–passage–answer triplets.… 31. **[A Fine-Grained Annotated Multi-Dialectal Arabic Corpus](https://md.research.elamur.ai/free/en/papers/charfi-2019-fine-grained-annotated-multi-dialectal/)** *(2019 · 11 citations)* Research on author profiling in Arabic has been limited because few resources exist for dialectal Arabic, and those that do rarely include speaker attributes such as age or gender. 32. **[Can Crowdsourcing be used for Effective Annotation of Arabic?](https://md.research.elamur.ai/free/en/papers/zaghouani-2014-can-crowdsourcing-be-used-effective/)** *(2014 · 10 citations)* The paper asks whether paid non-expert workers on Amazon Mechanical Turk (AMT) can do reliable linguistic annotation of Arabic. 33. **[Critical Survey of the Freely Available Arabic Corpora](https://md.research.elamur.ai/free/en/papers/zaghouani-2017-critical-survey-freely-available-arabic/)** *(2017 · 9 citations)* Researchers who cannot pay for licensed data often struggle to find Arabic corpora. Most well-known resources sit behind fees or memberships at LDC and ELRA. Free ones are scattered across personal pages, and the existing lists (LRE Map, the ACL wiki, ELSNET, MEDAR) are incomplete, outdated, or lack download links.… 34. **[SAHSOH@QALB-2015 Shared Task: A Rule-Based Correction Method of Common Arabic Native and Non-Native Speakers' Errors](https://md.research.elamur.ai/free/en/papers/zaghouani-2015-sahsoh-qalb-2015-shared-task/)** *(2015 · 8 citations)* This paper describes the authors' entry in the QALB-2015 shared task on automatic correction of Arabic text. 35. **[ThatiAR: Subjectivity Detection in Arabic News Sentences](https://md.research.elamur.ai/free/en/papers/suwaileh-2024-thatiar-subjectivity-detection-arabic-news/)** *(2024 · 7 citations)* Most subjectivity detection research has targeted English and other well-resourced languages. Arabic news has had no large dedicated dataset. The authors built ThatiAR, about 3.6K Arabic news sentences labeled by crowd workers as subjective or objective. Source articles came from fact-checked claims in AraFacts, plus… 36. **[QCAW 1.0: Building a Qatari Corpus of Student Argumentative Writing](https://md.research.elamur.ai/free/en/papers/zaghouani-2024-qcaw-1-0-building-qatari/)** *(2024 · 6 citations)* The paper describes QCAW, the Qatari Corpus of Argumentative Writing. It addresses a gap in learner-corpus resources: almost no bilingual data exist in which the same people write in their native Arabic and in English as a second language. The authors collected argumentative essays from 195 Qatari university… 37. **[Transformers and Ensemble methods: A solution for Hate Speech Detection in Arabic languages](https://md.research.elamur.ai/free/en/papers/paula-2023-transformers-ensemble-methods-solution-hate/)** *(2023 · 6 citations)* The paper describes a submission to the hate speech subtask (task 1.d) of the CERIST NLP Challenge 2022. The task asks a system to label Arabic tweets as Hateful or Not Hateful. Arabic social media text is largely dialectal and has relatively few resources, which makes the problem hard. The data are COVID-19… 38. **[Munazarat 1.0: A Corpus of Arabic Competitive Debates](https://md.research.elamur.ai/free/en/papers/khader-2024-munazarat-1-0-corpus-arabic/)** *(2024 · 5 citations)* Arabic NLP lacks open datasets compared with English and other major languages. Data on spoken argumentation is especially scarce, even though competitive debating is common across the Arab world. The authors built Munazarat 1.0, a corpus of roughly 50 hours of transcribed speech from 73 debates held at tournaments… 39. **[Can ChatGPT be Your Personal Medical Assistant?](https://md.research.elamur.ai/free/en/papers/biswas-2023-chatgpt-personal-medical-assistant/)** *(2023 · 5 citations)* The paper asks whether a fine-tuned commercial LLM can act as a medical question-answering assistant for Arabic speakers. 40. **[UPV at the Arabic Hate Speech 2022 Shared Task: Offensive Language and Hate Speech Detection using Transformers and Ensemble Models](https://md.research.elamur.ai/free/en/papers/paula-2022-upv-arabic-hate-speech-2022/)** *(2022 · 5 citations)* The authors tackle automatic detection of abusive content in Arabic tweets, many of which are written in dialect, as part of an OSACT 2022 competition focused on identifying hate speech at a fine-grained level. 41. **[Generating acceptable Arabic Core Vocabularies and Symbols for AAC users](https://md.research.elamur.ai/free/en/papers/draffan-2015-generating-acceptable-arabic-core-vocabularies/)** *(2015 · 5 citations)* Therapists and teachers in the Arabic-speaking Gulf often rely on Western symbol sets and English core vocabularies, which fit poorly with Arabic language and culture. 42. **[From Posts to Pressure: An Arabic Dataset about Stress and Mental-Health Monitoring](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-posts-pressure-arabic-dataset-about/)** *(2026 · 4 citations)* Arabic mental-health NLP has concentrated mostly on depression and suicidal ideation, usually with data from X. 43. **[Building a Corpus of Qatari Arabic Expressions](https://md.research.elamur.ai/free/en/papers/mulla-2020-building-corpus-qatari-arabic-expressions/)** *(2020 · 4 citations)* Arabic NLP resources focus mostly on Modern Standard Arabic. A few dialects, such as Egyptian and Levantine, have some coverage, but Gulf Arabic, and Qatari in particular, has almost none. The authors also argue that traditional Qatari vocabulary is disappearing as English spreads and younger speakers stop using… 44. **[Using Ambiguity Detection to Streamline Linguistic Annotation](https://md.research.elamur.ai/free/en/papers/zaghouani-2016-ambiguity-detection-streamline-linguistic-annotation/)** *(2016 · 4 citations)* Most written Arabic omits short vowels and other diacritics. This creates orthographic ambiguity on top of ordinary lexical ambiguity, and it makes building diacritized training corpora slow and error-prone. Within the OptDiac project, the authors test whether automatically flagging ambiguous words can make manual… 45. **[Applying the Cognitive Machine Translation Evaluation Approach to Arabic](https://md.research.elamur.ai/free/en/papers/temnikova-2016-applying-cognitive-machine-translation-evaluation/)** *(2016 · 3 citations)* The paper asks whether a cognitively motivated scheme for judging how hard machine-translated text is to post-edit, first built for Russian, Spanish and Bulgarian, still works for a typologically distant language, Modern Standard Arabic. 46. **[Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in Chinese](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-beyond-english-evasion-human-annotated/)** *(2026 · 2 citations)* Safety alignment built mainly on English data often fails in Chinese. There, users hide harmful requests with Pinyin spellings, homophones, characters split into radicals, underground slang (hēihuà), or hedged, curiosity-style wording. Existing Chinese and multilingual benchmarks mostly contain direct or… 47. **[KZ-SafetyPrompts: A Kazakh Safety Evaluation Prompt Dataset for Large Language Models](https://md.research.elamur.ai/free/en/papers/zaghouani-2026-kz-safetyprompts-kazakh-safety-evaluation/)** *(2026 · 2 citations)* Tools for testing how large language models handle harmful requests rarely cover Kazakh, and model safety behaviour is known to shift between languages. 48. **[Ahasis Shared Task: Hybrid Lexicon-Augmented AraBERT Model for Sentiment Detection in Arabic Dialects](https://md.research.elamur.ai/free/en/papers/ibrahim-2025-ahasis-shared-task-hybrid-lexicon/)** *(2025 · 2 citations)* The paper describes a system for the Ahasis@RANLP-2025 shared task, which asks for three-way sentiment classification (positive, neutral, negative) of hotel reviews written in Saudi Arabic and Darija (Moroccan Arabic). 49. **[Evaluation of Pretrained and Instruction-Based Pretrained Models for Emotion Detection in Arabic Social Media Text](https://md.research.elamur.ai/free/en/papers/biswas-2025-evaluation-pretrained-instruction-based-pretrained/)** *(2025 · 2 citations)* The paper asks which kind of model best detects emotions in Arabic tweets when one tweet can carry several emotions at once. 50. **[AHA-Memes: A Fine-Grained Multimodal Benchmark for Understanding Hate in Arabic Memes](https://md.research.elamur.ai/free/en/papers/kmainasi-2026-aha-memes-fine-grained-multimodal/)** *(2026 · 1 citation)* Hateful memes express hostility through the combination of picture, caption and shared cultural background. [← prev](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) [1](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/) **2** [3](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/3/) [next →](https://md.research.elamur.ai/free/en/authors/wajdi-zaghouani/page/3/)