<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nwesri-etal-2025-sentiment">
    <titleInfo>
        <title>Sentiment Analysis on Arabic Dialects: A Multi-Dialect Benchmark</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Abdusalam</namePart>
        <namePart type="given">F</namePart>
        <namePart type="given">Ahmad</namePart>
        <namePart type="family">Nwesri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nabila</namePart>
        <namePart type="given">Almabrouk</namePart>
        <namePart type="given">S</namePart>
        <namePart type="family">Shinbir</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Amani</namePart>
        <namePart type="given">Bahlul</namePart>
        <namePart type="family">Sharif</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Shared Task on Sentiment Analysis for Arabic Dialects</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maram</namePart>
            <namePart type="family">Alharbi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Salmane</namePart>
            <namePart type="family">Chafik</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Saad</namePart>
            <namePart type="family">Ezzini</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tharindu</namePart>
            <namePart type="family">Ranasinghe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hansi</namePart>
            <namePart type="family">Hettiarachchi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents our contribution to the AHASIS Shared Task at RANLP 2025, which focuses on sentiment analysis for Arabic dialects. While sentiment analysis has seen considerable progress in Modern Standard Arabic (MSA), the diversity and complexity of Arabic dialects pose unique challenges that remain underexplored. We address this by fine-tuning six pre-trained language models, including AraBERT, MARBERTv2, QARiB, and DarijaBERT, on a sentiment-labeled dataset comprising hotel reviews written in Saudi and Moroccan (Darija) dialects. Our experiments evaluate the models’ performance on both combined and individual dialect datasets. MARBERTv2 achieved the highest performance with an F1-score of 79% on the test set, securing third place among 14 participants. We further analyze the effectiveness of each model across dialects, demonstrating the importance of dialect-aware pretraining for Arabic sentiment analysis. Our findings highlight the value of leveraging large pre-trained models tailored to dialectal Arabic for improved sentiment classification.</abstract>
    <identifier type="citekey">nwesri-etal-2025-sentiment</identifier>
    <location>
        <url>https://aclanthology.org/2025.ranlp-ahasis.13/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>86</start>
            <end>91</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Sentiment Analysis on Arabic Dialects: A Multi-Dialect Benchmark
%A Nwesri, Abdusalam F. Ahmad
%A Shinbir, Nabila Almabrouk S.
%A Sharif, Amani Bahlul
%Y Alharbi, Maram
%Y Chafik, Salmane
%Y Ezzini, Saad
%Y Mitkov, Ruslan
%Y Ranasinghe, Tharindu
%Y Hettiarachchi, Hansi
%S Proceedings of the Shared Task on Sentiment Analysis for Arabic Dialects
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F nwesri-etal-2025-sentiment
%X This paper presents our contribution to the AHASIS Shared Task at RANLP 2025, which focuses on sentiment analysis for Arabic dialects. While sentiment analysis has seen considerable progress in Modern Standard Arabic (MSA), the diversity and complexity of Arabic dialects pose unique challenges that remain underexplored. We address this by fine-tuning six pre-trained language models, including AraBERT, MARBERTv2, QARiB, and DarijaBERT, on a sentiment-labeled dataset comprising hotel reviews written in Saudi and Moroccan (Darija) dialects. Our experiments evaluate the models’ performance on both combined and individual dialect datasets. MARBERTv2 achieved the highest performance with an F1-score of 79% on the test set, securing third place among 14 participants. We further analyze the effectiveness of each model across dialects, demonstrating the importance of dialect-aware pretraining for Arabic sentiment analysis. Our findings highlight the value of leveraging large pre-trained models tailored to dialectal Arabic for improved sentiment classification.
%U https://aclanthology.org/2025.ranlp-ahasis.13/
%P 86-91

Markdown (Informal)

[Sentiment Analysis on Arabic Dialects: A Multi-Dialect Benchmark](https://aclanthology.org/2025.ranlp-ahasis.13/) (Nwesri et al., RANLP 2025)

• Sentiment Analysis on Arabic Dialects: A Multi-Dialect Benchmark (Nwesri et al., RANLP 2025)

ACL

• Abdusalam F. Ahmad Nwesri, Nabila Almabrouk S. Shinbir, and Amani Bahlul Sharif. 2025. Sentiment Analysis on Arabic Dialects: A Multi-Dialect Benchmark. In Proceedings of the Shared Task on Sentiment Analysis for Arabic Dialects, pages 86–91, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.