@inproceedings{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",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.929/",
doi = "10.63317/363iym4fo7cx",
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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaghouani-etal-2026-arabdiscrim">
<titleInfo>
<title>ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shimaa</namePart>
<namePart type="given">Amer</namePart>
<namePart type="family">Ibrahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mabrouka</namePart>
<namePart type="family">Bessghaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">zaghouani-etal-2026-arabdiscrim</identifier>
<identifier type="doi">10.63317/363iym4fo7cx</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.929/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11874</start>
<end>11884</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination
%A Zaghouani, Wajdi
%A Ibrahim, Shimaa Amer
%A Bessghaier, Mabrouka
%A Bouamor, Houda
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F zaghouani-etal-2026-arabdiscrim
%X 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.
%R 10.63317/363iym4fo7cx
%U https://aclanthology.org/2026.lrec-1.929/
%U https://doi.org/10.63317/363iym4fo7cx
%P 11874-11884
Markdown (Informal)
[ArabDiscrim: A Decade-Long Arabic Facebook Corpus on Racism and Discrimination](https://aclanthology.org/2026.lrec-1.929/) (Zaghouani et al., LREC 2026)
ACL