Skip to content

ObfXhate: a large-scale Arabic dataset and transformer-based framework for detecting obfuscated hate speech

Sep 2026 · Language Resources and Evaluation · Vol 60 · 0 citations · 67 references
Computer Science

TL;DR

This work offers a robust benchmark dataset, a three-tier labeling framework, and insights into preprocessing strategies tailored to Arabic’s linguistic complexity, advancing the development of culturally aligned and ethically sound Arabic large language models for content moderation and beyond.

View source

Similar papers

Review Aug 2026

ArabiDeepfake: a multi-domain Arabic deepfake-text dataset and cross-domain detection benchmark

ArabiDeepfake provides detailed, reproducible protocols that advance robust Arabic deepfake detection and compares a pooled single model against a five-model ensemble against a five-model ensemble, reporting 95% CIs and McNemar tests.

Amal Sunba, Tarek Helmy · 0 citations
Open access Sep 2026

Building and Evaluating an Arabic Social-Media Dataset for Deepfake Text Detection

A high-quality Arabic dataset spanning six major dialects and seven distinct domains is compiled, providing a representative benchmark for real-world environments and suggesting that the model effectively identifies the stylistic and expressive markers inherent in synthetic conversational Arabic.

Budoor Bader Alshehri, Amal Sunba, Tarek Helmy · 0 citations
Open access Oct 2026

Benchmarking fastText, word2vec, and BERT on the MAQASID Dataset: A Closed-Domain Religious Resource

In this paper, we introduce MAQASID, a closed-domain dataset for exploring the optimal semantic representation of Indonesian Islamic texts. It is designed to solve challenges in low-resource languages and closed-domain religious datasets, such as Arabic-to-Indonesian transliteration inconsistencies and semantic shifts....

Muhammad Zidny Naf'an, E. Winarko, S. Priyanta · 0 citations
Open access Sep 2026

A Low-Resource Arabic Dataset and Transformer-Based Benchmark for Dark Pattern Detection in E-Commerce Mobile Applications

Per-class analysis shows every model struggles with several minority categories, indicating Arabic dark pattern detection remains genuinely difficult at current data volumes, indicating pre-training on dialectal, code-switched Arabic may matter more here than Arabic pre-training alone.

Reham Alabduljabbar · 0 citations
Open access Sep 2026

ANERD: A Large-Scale Arabic Corpus for Named Entity Recognition and Disambiguation

Arabic NER and NED research is limited by the lack of large-scale public datasets that support both tasks with validated entity links and difficulty-aware evaluation. In this paper, we propose ANERD, a large-scale Arabic corpus and benchmark for NER/NED, to overcome these drawbacks. ANERD includes 502,756 sentences fro...

M. Alotaibi, Mohamed El Bachir Menai · 0 citations
Open access Oct 2026

A Transformer-Based Framework for Offensive Language Detection in Kannada-English Code-Mixed Text

This paper explores the usefulness of multilingual transformer-based models in the detection of offensive language on Kannada-English code-mixed social media text. This work compares CNNTFIDF, XLMR, IndicBERT, and DistilBERT models, and suggests a better DistilBERT-related model using specific preprocessing and fine-tu...

S. Shilpashree, D. Ashoka · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.