@inproceedings{zaghouani-etal-2026-nakba,
title = "Nakba Discourse 2025: A Bilingual Social Media Dataset for Collective Trauma Analysis",
author = "Zaghouani, Wajdi and
Bessghaier, Mabrouka and
Attia, Kais",
editor = "Jarrar, Mustafa and
El-Haj, Mo and
Haddad, Amal and
Atiani, Serin and
Abudalfa, Shadi and
Regier, Terry and
Rayson, Paul and
Sima{'}an, Khalil and
Mansour, Camille",
booktitle = "Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma, Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.nakbanlp-1.3/",
doi = "10.63317/26i8wdd5eyrt",
pages = "33--42",
abstract = "We introduce Nakba Discourse 2025, a bilingual full-year social media dataset capturing Arabic and English discourse about the 1948 Palestinian Nakba across Twitter/X and Facebook from January to December 2025. The corpus contains 70,312 unique posts organized into intersecting sub-corpora by language, sentiment, gender, geography, and platform, with engagement metadata and automatically extracted rhetorical features. Analyses reveal systematic variation in engagement and framing across communities. Per-post engagement is highest in Israel and UK subsets (50.62 and 49.08 average likes respectively), while Arabic-language discourse shows markedly lower per-post engagement. Sentiment distribution is strongly skewed, with negative sentiment posts outnumbering positive ones at an 11:1 ratio (54,424 vs. 4,827 posts). Despite dramatic variation in absolute engagement levels, virality rates remain structurally constant at approximately 10{\%} across all Twitter/X sub-corpora, regardless of language, gender, or geography, pointing to platform-level amplification regularities. Gender analysis reveals that women achieve proportional virality equal to men despite producing roughly one-third the volume of posts. Temporal patterns align with cultural calendars, including Thursday peaks associated with Jumu{'}ah across Arabic and female subsets, and Sunday peaks in English-language subsets reflecting Western media cycles. The dataset will be released for research use and supports multilingual stance detection, virality modeling, rhetorical analysis, and computational studies of digital political memory."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaghouani-etal-2026-nakba">
<titleInfo>
<title>Nakba Discourse 2025: A Bilingual Social Media Dataset for Collective Trauma Analysis</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">Mabrouka</namePart>
<namePart type="family">Bessghaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kais</namePart>
<namePart type="family">Attia</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 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mustafa</namePart>
<namePart type="family">Jarrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mo</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amal</namePart>
<namePart type="family">Haddad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serin</namePart>
<namePart type="family">Atiani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shadi</namePart>
<namePart type="family">Abudalfa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Terry</namePart>
<namePart type="family">Regier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Rayson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Sima’an</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camille</namePart>
<namePart type="family">Mansour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Nakba Discourse 2025, a bilingual full-year social media dataset capturing Arabic and English discourse about the 1948 Palestinian Nakba across Twitter/X and Facebook from January to December 2025. The corpus contains 70,312 unique posts organized into intersecting sub-corpora by language, sentiment, gender, geography, and platform, with engagement metadata and automatically extracted rhetorical features. Analyses reveal systematic variation in engagement and framing across communities. Per-post engagement is highest in Israel and UK subsets (50.62 and 49.08 average likes respectively), while Arabic-language discourse shows markedly lower per-post engagement. Sentiment distribution is strongly skewed, with negative sentiment posts outnumbering positive ones at an 11:1 ratio (54,424 vs. 4,827 posts). Despite dramatic variation in absolute engagement levels, virality rates remain structurally constant at approximately 10% across all Twitter/X sub-corpora, regardless of language, gender, or geography, pointing to platform-level amplification regularities. Gender analysis reveals that women achieve proportional virality equal to men despite producing roughly one-third the volume of posts. Temporal patterns align with cultural calendars, including Thursday peaks associated with Jumu’ah across Arabic and female subsets, and Sunday peaks in English-language subsets reflecting Western media cycles. The dataset will be released for research use and supports multilingual stance detection, virality modeling, rhetorical analysis, and computational studies of digital political memory.</abstract>
<identifier type="citekey">zaghouani-etal-2026-nakba</identifier>
<identifier type="doi">10.63317/26i8wdd5eyrt</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.3/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>33</start>
<end>42</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nakba Discourse 2025: A Bilingual Social Media Dataset for Collective Trauma Analysis
%A Zaghouani, Wajdi
%A Bessghaier, Mabrouka
%A Attia, Kais
%Y Jarrar, Mustafa
%Y El-Haj, Mo
%Y Haddad, Amal
%Y Atiani, Serin
%Y Abudalfa, Shadi
%Y Regier, Terry
%Y Rayson, Paul
%Y Sima’an, Khalil
%Y Mansour, Camille
%S Proceedings of the 2nd International Workshop on Nakba Narratives as Language Resources @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma, Mallorca (Spain)
%F zaghouani-etal-2026-nakba
%X We introduce Nakba Discourse 2025, a bilingual full-year social media dataset capturing Arabic and English discourse about the 1948 Palestinian Nakba across Twitter/X and Facebook from January to December 2025. The corpus contains 70,312 unique posts organized into intersecting sub-corpora by language, sentiment, gender, geography, and platform, with engagement metadata and automatically extracted rhetorical features. Analyses reveal systematic variation in engagement and framing across communities. Per-post engagement is highest in Israel and UK subsets (50.62 and 49.08 average likes respectively), while Arabic-language discourse shows markedly lower per-post engagement. Sentiment distribution is strongly skewed, with negative sentiment posts outnumbering positive ones at an 11:1 ratio (54,424 vs. 4,827 posts). Despite dramatic variation in absolute engagement levels, virality rates remain structurally constant at approximately 10% across all Twitter/X sub-corpora, regardless of language, gender, or geography, pointing to platform-level amplification regularities. Gender analysis reveals that women achieve proportional virality equal to men despite producing roughly one-third the volume of posts. Temporal patterns align with cultural calendars, including Thursday peaks associated with Jumu’ah across Arabic and female subsets, and Sunday peaks in English-language subsets reflecting Western media cycles. The dataset will be released for research use and supports multilingual stance detection, virality modeling, rhetorical analysis, and computational studies of digital political memory.
%R 10.63317/26i8wdd5eyrt
%U https://aclanthology.org/2026.nakbanlp-1.3/
%U https://doi.org/10.63317/26i8wdd5eyrt
%P 33-42
Markdown (Informal)
[Nakba Discourse 2025: A Bilingual Social Media Dataset for Collective Trauma Analysis](https://aclanthology.org/2026.nakbanlp-1.3/) (Zaghouani et al., NakbaNLP 2026)
ACL