@inproceedings{shlkamy-zaghouani-2026-northwestern-dialectsenteval,
title = "Northwestern at {D}ialect{S}ent{E}val 2026: A Comparative Study of {MARBERT}v2 and {A}ra{BERT} for {A}rabic Dialect Sentiment Analysis",
author = "Shlkamy, Eman Sedqy and
Zaghouani, Wajdi",
editor = "Abdul-Mageed, Muhammad and
Elsayed, Tamer and
Bouamor, Houda and
El-Beltagy, Samhaa and
Al-Khalifa, Hend and
Abdelali, Ahmed and
Elmadany, AbdelRahim and
El Mekki, Abdellah and
Darwish, Kareem and
Alkhereyf, Sakhar and
Luqman, Hamzah and
Khalifa, Salam and
Magdy, Samar and
Alyafeai, Zaid and
Hamed, Injy and
Zaghouani, Wajdi and
Zitouni, Imed",
booktitle = "Proceedings of The Fourth {A}rabic Natural Language Processing Conference: Shared Tasks",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.arabicnlp-sharedtasks.177/",
pages = "1409--1413",
ISBN = "979-8-89176-497-2",
abstract = "This paper describes our submission to \textbf{Subtask 1 of DialectSentEval 2026}, which focuses on three class sentiment classification for Arabic dialectal text. The task aims to classify sentences written in five Arabic dialects into \textit{positive}, \textit{negative}, or \textit{neutral} sentiment categories. We investigate the effectiveness of transformer-based Arabic language models through a series of controlled experiments. Specifically, we compare MARBERTv2 and AraBERT while maintaining identical pre processing, training, and evaluation settings to ensure a fair comparison. In addition, we examine whether explicitly providing dialect information as part of the input improves classification performance.\par Experimental results on an internal validation split show that MARBERTv2 consistently outperforms AraBERT on this task. Furthermore, removing the explicit dialect tag from the input slightly improves performance, suggesting that MARBERTv2 can effectively capture dialect-specific linguistic patterns directly from the sentence. Our best configuration, which uses MARBERTv2 with sentence-only input, achieves a Macro F1-score of \textbf{0.9394} and an accuracy of \textbf{94.24{\%}}. These findings demonstrate the effectiveness of dialect-aware pre-trained language models for Arabic sentiment analysis and establish a strong baseline for the official shared task evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shlkamy-zaghouani-2026-northwestern-dialectsenteval">
<titleInfo>
<title>Northwestern at DialectSentEval 2026: A Comparative Study of MARBERTv2 and AraBERT for Arabic Dialect Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eman</namePart>
<namePart type="given">Sedqy</namePart>
<namePart type="family">Shlkamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdul-Mageed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">AbdelRahim</namePart>
<namePart type="family">Elmadany</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdellah</namePart>
<namePart type="family">El Mekki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamzah</namePart>
<namePart type="family">Luqman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zaid</namePart>
<namePart type="family">Alyafeai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Injy</namePart>
<namePart type="family">Hamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-497-2</identifier>
</relatedItem>
<abstract>This paper describes our submission to Subtask 1 of DialectSentEval 2026, which focuses on three class sentiment classification for Arabic dialectal text. The task aims to classify sentences written in five Arabic dialects into positive, negative, or neutral sentiment categories. We investigate the effectiveness of transformer-based Arabic language models through a series of controlled experiments. Specifically, we compare MARBERTv2 and AraBERT while maintaining identical pre processing, training, and evaluation settings to ensure a fair comparison. In addition, we examine whether explicitly providing dialect information as part of the input improves classification performance.\par Experimental results on an internal validation split show that MARBERTv2 consistently outperforms AraBERT on this task. Furthermore, removing the explicit dialect tag from the input slightly improves performance, suggesting that MARBERTv2 can effectively capture dialect-specific linguistic patterns directly from the sentence. Our best configuration, which uses MARBERTv2 with sentence-only input, achieves a Macro F1-score of 0.9394 and an accuracy of 94.24%. These findings demonstrate the effectiveness of dialect-aware pre-trained language models for Arabic sentiment analysis and establish a strong baseline for the official shared task evaluation.</abstract>
<identifier type="citekey">shlkamy-zaghouani-2026-northwestern-dialectsenteval</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.177/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1409</start>
<end>1413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Northwestern at DialectSentEval 2026: A Comparative Study of MARBERTv2 and AraBERT for Arabic Dialect Sentiment Analysis
%A Shlkamy, Eman Sedqy
%A Zaghouani, Wajdi
%Y Abdul-Mageed, Muhammad
%Y Elsayed, Tamer
%Y Bouamor, Houda
%Y El-Beltagy, Samhaa
%Y Al-Khalifa, Hend
%Y Abdelali, Ahmed
%Y Elmadany, AbdelRahim
%Y El Mekki, Abdellah
%Y Darwish, Kareem
%Y Alkhereyf, Sakhar
%Y Luqman, Hamzah
%Y Khalifa, Salam
%Y Magdy, Samar
%Y Alyafeai, Zaid
%Y Hamed, Injy
%Y Zaghouani, Wajdi
%Y Zitouni, Imed
%S Proceedings of The Fourth Arabic Natural Language Processing Conference: Shared Tasks
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-497-2
%F shlkamy-zaghouani-2026-northwestern-dialectsenteval
%X This paper describes our submission to Subtask 1 of DialectSentEval 2026, which focuses on three class sentiment classification for Arabic dialectal text. The task aims to classify sentences written in five Arabic dialects into positive, negative, or neutral sentiment categories. We investigate the effectiveness of transformer-based Arabic language models through a series of controlled experiments. Specifically, we compare MARBERTv2 and AraBERT while maintaining identical pre processing, training, and evaluation settings to ensure a fair comparison. In addition, we examine whether explicitly providing dialect information as part of the input improves classification performance.\par Experimental results on an internal validation split show that MARBERTv2 consistently outperforms AraBERT on this task. Furthermore, removing the explicit dialect tag from the input slightly improves performance, suggesting that MARBERTv2 can effectively capture dialect-specific linguistic patterns directly from the sentence. Our best configuration, which uses MARBERTv2 with sentence-only input, achieves a Macro F1-score of 0.9394 and an accuracy of 94.24%. These findings demonstrate the effectiveness of dialect-aware pre-trained language models for Arabic sentiment analysis and establish a strong baseline for the official shared task evaluation.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.177/
%P 1409-1413
Markdown (Informal)
[Northwestern at DialectSentEval 2026: A Comparative Study of MARBERTv2 and AraBERT for Arabic Dialect Sentiment Analysis](https://aclanthology.org/2026.arabicnlp-sharedtasks.177/) (Shlkamy & Zaghouani, ArabicNLP 2026)
ACL