@article{zaghouani-etal-2026-arabdiscrim,
    title = "{A}rab{D}iscrim: A Decade-Long {A}rabic {F}acebook Corpus on Racism and Discrimination",
    author = "Zaghouani, Wajdi  and
      Ibrahim, Shimaa Amer  and
      Bessghaier, Mabrouka  and
      Bouamor, Houda",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.929/",
    pages = "11874--11884",
    abstract = "We present ArabDiscrim, a decade-long lexical resource and corpus of 293K public Arabic Facebook posts (2014{--}2024) discussing racism and discrimination. Unlike existing Twitter-centric datasets, ArabDiscrim integrates platform-native engagement signals, including reactions, shares, comments, and page metadata, enabling joint analysis of language and audience response. The resource includes 200 curated terms (100 racism, 100 discrimination) with morphological regex families (13+ inflections per lemma), and 20 discrimination axes capturing identity-based grounds for unequal treatment. It also provides explicit attribution patterns. Released under a restricted research-use license for ethical compliance with platform terms, ArabDiscrim supports weak supervision, axis-aware sampling, and platform ecology research. By bridging lexical depth and ecological validity, it establishes a foundation for fairness-oriented, platform-aware Arabic NLP."
}