<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hamdy-etal-2026-comparative">
    <titleInfo>
        <title>A Comparative Study of Arabic Sentiment Swap Models for AraSentEval 2026</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yumna</namePart>
        <namePart type="family">Hamdy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mohab</namePart>
        <namePart type="family">ElDamhougy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yomna</namePart>
        <namePart type="family">Eid</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ensaf</namePart>
        <namePart type="family">Hussein</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>The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks</title>
        </titleInfo>
        <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">Mo</namePart>
            <namePart type="family">El-Haj</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>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Palma, Mallorca (Spain)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Sentiment swap is a controlled text generation task that rewrites a sentence by inverting its sentiment polarity while preserving semantic content and fluency. In this paper, we present our system for AraSentEval 2026 Subtask 2 on Arabic sentiment swap, a particularly challenging problem due to Arabic’s rich morphology and dialectal variation. We investigate multiple modeling paradigms, including encoder–decoder and multilingual approaches, and propose an enhanced system that combines targeted data augmentation and ensemble learning. Specifically, we augment underrepresented dialectal patterns to improve robustness and ensemble two Arabic-focused sequence-to-sequence models, AraBART and AraT5v2. Experiments are conducted on the MA’aks parallel dataset under fine-tuned settings. Our system ranked first in AraSentEval 2026 Subtask 2, achieving a BLEU score of 43.0, chrF of 65.36, and sentiment preservation accuracy of 0.7554. The results demonstrate that dialect-aware augmentation together with model ensembling substantially improves sentiment-controlled generation in Arabic and establishes strong baselines for future research in low-resource sentiment manipulation. Keywords: Arabic NLP, sentiment swap, style transfer, AraSentEval, text generation</abstract>
    <identifier type="citekey">hamdy-etal-2026-comparative</identifier>
    <identifier type="doi">10.63317/5effrrzp6ew2</identifier>
    <location>
        <url>https://aclanthology.org/2026.osact-1.36/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>269</start>
            <end>273</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Comparative Study of Arabic Sentiment Swap Models for AraSentEval 2026
%A Hamdy, Yumna
%A ElDamhougy, Mohab
%A Eid, Yomna
%A Hussein, Ensaf
%Y Al-Khalifa, Hend
%Y El-Haj, Mo
%Y Ezzini, Saad
%S The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks
%D 2026
%8 May
%I Association for Computational Linguistics
%C Palma, Mallorca (Spain)
%F hamdy-etal-2026-comparative
%X Sentiment swap is a controlled text generation task that rewrites a sentence by inverting its sentiment polarity while preserving semantic content and fluency. In this paper, we present our system for AraSentEval 2026 Subtask 2 on Arabic sentiment swap, a particularly challenging problem due to Arabic’s rich morphology and dialectal variation. We investigate multiple modeling paradigms, including encoder–decoder and multilingual approaches, and propose an enhanced system that combines targeted data augmentation and ensemble learning. Specifically, we augment underrepresented dialectal patterns to improve robustness and ensemble two Arabic-focused sequence-to-sequence models, AraBART and AraT5v2. Experiments are conducted on the MA’aks parallel dataset under fine-tuned settings. Our system ranked first in AraSentEval 2026 Subtask 2, achieving a BLEU score of 43.0, chrF of 65.36, and sentiment preservation accuracy of 0.7554. The results demonstrate that dialect-aware augmentation together with model ensembling substantially improves sentiment-controlled generation in Arabic and establishes strong baselines for future research in low-resource sentiment manipulation. Keywords: Arabic NLP, sentiment swap, style transfer, AraSentEval, text generation
%R 10.63317/5effrrzp6ew2
%U https://aclanthology.org/2026.osact-1.36/
%U https://doi.org/10.63317/5effrrzp6ew2
%P 269-273

Markdown (Informal)

[A Comparative Study of Arabic Sentiment Swap Models for AraSentEval 2026](https://aclanthology.org/2026.osact-1.36/) (Hamdy et al., OSACT 2026)

• A Comparative Study of Arabic Sentiment Swap Models for AraSentEval 2026 (Hamdy et al., OSACT 2026)

ACL

• Yumna Hamdy, Mohab ElDamhougy, Yomna Eid, and Ensaf Hussein. 2026. A Comparative Study of Arabic Sentiment Swap Models for AraSentEval 2026. In The 7th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT7) with 5 Shared Tasks, pages 269–273, Palma, Mallorca (Spain). Association for Computational Linguistics.