@inproceedings{bahgat-etal-2026-resistant,
title = "The Resistant Word at {S}tance{N}akba Shared Task: A Topic-Aware Model for Cross-Topic Stance Detection",
author = "Bahgat, Mohamed and
Salah, Doaa and
Yassine, Sarah",
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-1.24/",
doi = "10.63317/33r5jdoe6avj",
pages = "182--186",
abstract = "Cross-topic stance detection in Arabic is the task of identifying whether a text expresses a pro, against, or neutral position toward a given issue, and it is particularly challenging under topic shifts and class imbalance. In Subtask B of the StanceNakba 2026 shared task on Arabic cross-topic stance detection, we are given a Levantine Arabic sentence and one of two topics: ``Normalization with Israel'' or ``Refugee/Immigrant Presence in Jordan,'' and we must classify the expressed stance. A central difficulty is the systematic failure of standard fine-tuning to recognize the minority neutral class, driven by majority-class dominance in cross-entropy training and accuracy-based checkpoint selection. To address this, we combine random oversampling with class-weighted cross-entropy loss, and we build an ensemble of four Arabic pre-trained transformers MARBERT, AraBERT Large, XLM-RoBERTa Base, and CAMeL-BERT Mix each trained using Stratified 5-Fold cross-validation. Our final system achieves a macro-F1 of 0.9777 and an accuracy of 97.79{\%} on the evaluation set."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahgat-etal-2026-resistant">
<titleInfo>
<title>The Resistant Word at StanceNakba Shared Task: A Topic-Aware Model for Cross-Topic Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Bahgat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doaa</namePart>
<namePart type="family">Salah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Yassine</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>Cross-topic stance detection in Arabic is the task of identifying whether a text expresses a pro, against, or neutral position toward a given issue, and it is particularly challenging under topic shifts and class imbalance. In Subtask B of the StanceNakba 2026 shared task on Arabic cross-topic stance detection, we are given a Levantine Arabic sentence and one of two topics: “Normalization with Israel” or “Refugee/Immigrant Presence in Jordan,” and we must classify the expressed stance. A central difficulty is the systematic failure of standard fine-tuning to recognize the minority neutral class, driven by majority-class dominance in cross-entropy training and accuracy-based checkpoint selection. To address this, we combine random oversampling with class-weighted cross-entropy loss, and we build an ensemble of four Arabic pre-trained transformers MARBERT, AraBERT Large, XLM-RoBERTa Base, and CAMeL-BERT Mix each trained using Stratified 5-Fold cross-validation. Our final system achieves a macro-F1 of 0.9777 and an accuracy of 97.79% on the evaluation set.</abstract>
<identifier type="citekey">bahgat-etal-2026-resistant</identifier>
<identifier type="doi">10.63317/33r5jdoe6avj</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.24/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>182</start>
<end>186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Resistant Word at StanceNakba Shared Task: A Topic-Aware Model for Cross-Topic Stance Detection
%A Bahgat, Mohamed
%A Salah, Doaa
%A Yassine, Sarah
%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 bahgat-etal-2026-resistant
%X Cross-topic stance detection in Arabic is the task of identifying whether a text expresses a pro, against, or neutral position toward a given issue, and it is particularly challenging under topic shifts and class imbalance. In Subtask B of the StanceNakba 2026 shared task on Arabic cross-topic stance detection, we are given a Levantine Arabic sentence and one of two topics: “Normalization with Israel” or “Refugee/Immigrant Presence in Jordan,” and we must classify the expressed stance. A central difficulty is the systematic failure of standard fine-tuning to recognize the minority neutral class, driven by majority-class dominance in cross-entropy training and accuracy-based checkpoint selection. To address this, we combine random oversampling with class-weighted cross-entropy loss, and we build an ensemble of four Arabic pre-trained transformers MARBERT, AraBERT Large, XLM-RoBERTa Base, and CAMeL-BERT Mix each trained using Stratified 5-Fold cross-validation. Our final system achieves a macro-F1 of 0.9777 and an accuracy of 97.79% on the evaluation set.
%R 10.63317/33r5jdoe6avj
%U https://aclanthology.org/2026.nakbanlp-1.24/
%U https://doi.org/10.63317/33r5jdoe6avj
%P 182-186
Markdown (Informal)
[The Resistant Word at StanceNakba Shared Task: A Topic-Aware Model for Cross-Topic Stance Detection](https://aclanthology.org/2026.nakbanlp-1.24/) (Bahgat et al., NakbaNLP 2026)
ACL