@inproceedings{adam-2026-faisalm93,
title = "faisalm93 at {D}ialect{S}ent{E}val 2026: A Five-Fold {MARBERT}v2 Ensemble for {A}rabic Dialect Sentiment Analysis",
author = "Adam, Faisal Muhammad",
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.183/",
pages = "1441--1445",
ISBN = "979-8-89176-497-2",
abstract = "We describe our submission to DialectSentEval 2026 Subtask 1, a three-class sentiment task covering Moroccan, Egyptian, Lebanese, Jordanian, and Saudi Arabic. Our system fine-tunes MARBERTv2 in five stratified folds and averages their test probabilities. Using raw text without explicit dialect conditioning or external task-specific data, the official submission obtained 0.7939 macro-F1, 0.8152 accuracy, 0.7917 macro precision, and 0.7987 macro recall, ranking eighth among twelve systems in the supplied snapshot. Separately, a post-submission character 3-5-gram diagnostic falls from 0.9157 OOF macro-F1 with row-stratified folds to 0.7520 when repeated ID-label groups and normalized duplicates are kept together. This result establishes dataset-level split sensitivity; it does not quantify the effect on MARBERTv2. We document the submitted configuration, a group-aware diagnostic protocol, and the experiments still needed to isolate the effects of strict splitting and ensembling on the transformer system."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adam-2026-faisalm93">
<titleInfo>
<title>faisalm93 at DialectSentEval 2026: A Five-Fold MARBERTv2 Ensemble for Arabic Dialect Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Faisal</namePart>
<namePart type="given">Muhammad</namePart>
<namePart type="family">Adam</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 describe our submission to DialectSentEval 2026 Subtask 1, a three-class sentiment task covering Moroccan, Egyptian, Lebanese, Jordanian, and Saudi Arabic. Our system fine-tunes MARBERTv2 in five stratified folds and averages their test probabilities. Using raw text without explicit dialect conditioning or external task-specific data, the official submission obtained 0.7939 macro-F1, 0.8152 accuracy, 0.7917 macro precision, and 0.7987 macro recall, ranking eighth among twelve systems in the supplied snapshot. Separately, a post-submission character 3-5-gram diagnostic falls from 0.9157 OOF macro-F1 with row-stratified folds to 0.7520 when repeated ID-label groups and normalized duplicates are kept together. This result establishes dataset-level split sensitivity; it does not quantify the effect on MARBERTv2. We document the submitted configuration, a group-aware diagnostic protocol, and the experiments still needed to isolate the effects of strict splitting and ensembling on the transformer system.</abstract>
<identifier type="citekey">adam-2026-faisalm93</identifier>
<location>
<url>https://aclanthology.org/2026.arabicnlp-sharedtasks.183/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1441</start>
<end>1445</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T faisalm93 at DialectSentEval 2026: A Five-Fold MARBERTv2 Ensemble for Arabic Dialect Sentiment Analysis
%A Adam, Faisal Muhammad
%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 adam-2026-faisalm93
%X We describe our submission to DialectSentEval 2026 Subtask 1, a three-class sentiment task covering Moroccan, Egyptian, Lebanese, Jordanian, and Saudi Arabic. Our system fine-tunes MARBERTv2 in five stratified folds and averages their test probabilities. Using raw text without explicit dialect conditioning or external task-specific data, the official submission obtained 0.7939 macro-F1, 0.8152 accuracy, 0.7917 macro precision, and 0.7987 macro recall, ranking eighth among twelve systems in the supplied snapshot. Separately, a post-submission character 3-5-gram diagnostic falls from 0.9157 OOF macro-F1 with row-stratified folds to 0.7520 when repeated ID-label groups and normalized duplicates are kept together. This result establishes dataset-level split sensitivity; it does not quantify the effect on MARBERTv2. We document the submitted configuration, a group-aware diagnostic protocol, and the experiments still needed to isolate the effects of strict splitting and ensembling on the transformer system.
%U https://aclanthology.org/2026.arabicnlp-sharedtasks.183/
%P 1441-1445
Markdown (Informal)
[faisalm93 at DialectSentEval 2026: A Five-Fold MARBERTv2 Ensemble for Arabic Dialect Sentiment Analysis](https://aclanthology.org/2026.arabicnlp-sharedtasks.183/) (Adam, ArabicNLP 2026)
ACL