@inproceedings{duridi-etal-2026-ptuk-nlp,
title = "{PTUK}-{NLP} at the {D}ialect{S}ent{E}val 2026 Shared Task: {MARBERT}-Based Sentiment Classification, Missing-Dialect Effects, and Error Analysis",
author = "Duridi, Tasneem and
Khaleel, Balsam and
Mallak, Asma Murad and
Jaber, Areej and
Jaber, Elaa",
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.180/",
pages = "1426--1430",
ISBN = "979-8-89176-497-2",
abstract = "We present our system for Subtask{~}1 (three-class sentiment classification) of the DialectSentEval 2026 shared task, which evaluates five Arabic dialects using the Multi-Dialect-Sent (MDS-3) hotel-review corpus. Our approach fine-tunes MARBERT with a stratified train/validation split and class-weighted cross-entropy loss. On the official test set, our system achieves an F1 score of 0.8175 and an accuracy of 0.8419, ranking 3rd on the official leaderboard. We identify a substantial dialect mismatch in the dataset: the training set contains no Lebanese reviews, while approximately 20{\%} of the test set is Lebanese. Adding additional Lebanese reviews from OCLAR partially reduces this gap, but does not eliminate it. The error analysis also shows that misclassifications are concentrated in the neutral class and in reviews that express mixed feelings, often with high confidence. These findings highlight the challenges of cross-dialect sentiment classification under unseen-dialect conditions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="duridi-etal-2026-ptuk-nlp">
<titleInfo>
<title>PTUK-NLP at the DialectSentEval 2026 Shared Task: MARBERT-Based Sentiment Classification, Missing-Dialect Effects, and Error Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tasneem</namePart>
<namePart type="family">Duridi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balsam</namePart>
<namePart type="family">Khaleel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="given">Murad</namePart>
<namePart type="family">Mallak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Areej</namePart>
<namePart type="family">Jaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elaa</namePart>
<namePart type="family">Jaber</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>We present our system for Subtask 1 (three-class sentiment classification) of the DialectSentEval 2026 shared task, which evaluates five Arabic dialects using the Multi-Dialect-Sent (MDS-3) hotel-review corpus. Our approach fine-tunes MARBERT with a stratified train/validation split and class-weighted cross-entropy loss. On the official test set, our system achieves an F1 score of 0.8175 and an accuracy of 0.8419, ranking 3rd on the official leaderboard. We identify a substantial dialect mismatch in the dataset: the training set contains no Lebanese reviews, while approximately 20% of the test set is Lebanese. Adding additional Lebanese reviews from OCLAR partially reduces this gap, but does not eliminate it. The error analysis also shows that misclassifications are concentrated in the neutral class and in reviews that express mixed feelings, often with high confidence. These findings highlight the challenges of cross-dialect sentiment classification under unseen-dialect conditions.</abstract>
<identifier type="citekey">duridi-etal-2026-ptuk-nlp</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.180/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1426</start>
<end>1430</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PTUK-NLP at the DialectSentEval 2026 Shared Task: MARBERT-Based Sentiment Classification, Missing-Dialect Effects, and Error Analysis
%A Duridi, Tasneem
%A Khaleel, Balsam
%A Mallak, Asma Murad
%A Jaber, Areej
%A Jaber, Elaa
%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 duridi-etal-2026-ptuk-nlp
%X We present our system for Subtask 1 (three-class sentiment classification) of the DialectSentEval 2026 shared task, which evaluates five Arabic dialects using the Multi-Dialect-Sent (MDS-3) hotel-review corpus. Our approach fine-tunes MARBERT with a stratified train/validation split and class-weighted cross-entropy loss. On the official test set, our system achieves an F1 score of 0.8175 and an accuracy of 0.8419, ranking 3rd on the official leaderboard. We identify a substantial dialect mismatch in the dataset: the training set contains no Lebanese reviews, while approximately 20% of the test set is Lebanese. Adding additional Lebanese reviews from OCLAR partially reduces this gap, but does not eliminate it. The error analysis also shows that misclassifications are concentrated in the neutral class and in reviews that express mixed feelings, often with high confidence. These findings highlight the challenges of cross-dialect sentiment classification under unseen-dialect conditions.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.180/
%P 1426-1430
Markdown (Informal)
[PTUK-NLP at the DialectSentEval 2026 Shared Task: MARBERT-Based Sentiment Classification, Missing-Dialect Effects, and Error Analysis](https://aclanthology.org/2026.arabicnlp-sharedtasks.180/) (Duridi et al., ArabicNLP 2026)
ACL