@inproceedings{nairat-nairat-2026-a2nlp,
title = "{A}2{NLP} at {S}tance{N}akba Shared Task: Fine-Tuned {A}ra{BERT} for Topic-Based {A}rabic Stance Detection",
author = "Nairat, Alaa and
Nairat, Aysar Mahmoud",
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-1.20/",
doi = "10.63317/5jy5nrvfrzzk",
pages = "147--159",
abstract = "AbstractThis paper describes A2NLP{'}s system for Subtask B of the StanceNakba Shared Task, which addresses cross-topic Arabic stance detection. The goal is to classify sentence{--}topic pairs into pro, against, or neutral labels. We introduce a topic-conditioned prompting strategy built on AraBERTv0.2-Twitter, where each instance is reformulated into a structured prompt that explicitly models the interaction between the sentence and its target topic. The model is trained using 5-fold stratified cross-validation with class-weighted loss to ensure robustness under mild label imbalance. Our final submission achieves a Macro-F1 score of 0.8483 on the official test set, outperforming the AraBERTv2 baseline (0.810) and ranking fifth overall. Ablation analysis confirms that topic-conditioned prompting substantially improves generalization across topics. The findings demonstrate the importance of structured input design and domain-aligned pretraining for reliable stance detection in dialectal Arabic social media discourse."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nairat-nairat-2026-a2nlp">
<titleInfo>
<title>A2NLP at StanceNakba Shared Task: Fine-Tuned AraBERT for Topic-Based Arabic Stance Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alaa</namePart>
<namePart type="family">Nairat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aysar</namePart>
<namePart type="given">Mahmoud</namePart>
<namePart type="family">Nairat</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>AbstractThis paper describes A2NLP’s system for Subtask B of the StanceNakba Shared Task, which addresses cross-topic Arabic stance detection. The goal is to classify sentence–topic pairs into pro, against, or neutral labels. We introduce a topic-conditioned prompting strategy built on AraBERTv0.2-Twitter, where each instance is reformulated into a structured prompt that explicitly models the interaction between the sentence and its target topic. The model is trained using 5-fold stratified cross-validation with class-weighted loss to ensure robustness under mild label imbalance. Our final submission achieves a Macro-F1 score of 0.8483 on the official test set, outperforming the AraBERTv2 baseline (0.810) and ranking fifth overall. Ablation analysis confirms that topic-conditioned prompting substantially improves generalization across topics. The findings demonstrate the importance of structured input design and domain-aligned pretraining for reliable stance detection in dialectal Arabic social media discourse.</abstract>
<identifier type="citekey">nairat-nairat-2026-a2nlp</identifier>
<identifier type="doi">10.63317/5jy5nrvfrzzk</identifier>
<location>
<url>https://aclanthology.org/2026.nakbanlp-1.20/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>147</start>
<end>159</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A2NLP at StanceNakba Shared Task: Fine-Tuned AraBERT for Topic-Based Arabic Stance Detection
%A Nairat, Alaa
%A Nairat, Aysar Mahmoud
%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 nairat-nairat-2026-a2nlp
%X AbstractThis paper describes A2NLP’s system for Subtask B of the StanceNakba Shared Task, which addresses cross-topic Arabic stance detection. The goal is to classify sentence–topic pairs into pro, against, or neutral labels. We introduce a topic-conditioned prompting strategy built on AraBERTv0.2-Twitter, where each instance is reformulated into a structured prompt that explicitly models the interaction between the sentence and its target topic. The model is trained using 5-fold stratified cross-validation with class-weighted loss to ensure robustness under mild label imbalance. Our final submission achieves a Macro-F1 score of 0.8483 on the official test set, outperforming the AraBERTv2 baseline (0.810) and ranking fifth overall. Ablation analysis confirms that topic-conditioned prompting substantially improves generalization across topics. The findings demonstrate the importance of structured input design and domain-aligned pretraining for reliable stance detection in dialectal Arabic social media discourse.
%R 10.63317/5jy5nrvfrzzk
%U https://aclanthology.org/2026.nakbanlp-1.20/
%U https://doi.org/10.63317/5jy5nrvfrzzk
%P 147-159
Markdown (Informal)
[A2NLP at StanceNakba Shared Task: Fine-Tuned AraBERT for Topic-Based Arabic Stance Detection](https://aclanthology.org/2026.nakbanlp-1.20/) (Nairat & Nairat, NakbaNLP 2026)
ACL