@inproceedings{shah-etal-2024-mememind,
title = "{M}eme{M}ind at {A}r{AIE}val Shared Task: Generative Augmentation and Feature Fusion for Multimodal Propaganda Detection in {A}rabic Memes through Advanced Language and Vision Models",
author = "Shah, Uzair and
Biswas, Md. Rafiul and
Agus, Marco and
Househ, Mowafa and
Zaghouani, Wajdi",
editor = "Habash, Nizar and
Bouamor, Houda and
Eskander, Ramy and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Abdelali, Ahmed and
Touileb, Samia and
Hamed, Injy and
Onaizan, Yaser and
Alhafni, Bashar and
Antoun, Wissam and
Khalifa, Salam and
Haddad, Hatem and
Zitouni, Imed and
AlKhamissi, Badr and
Almatham, Rawan and
Mrini, Khalil",
booktitle = "Proceedings of the Second Arabic Natural Language Processing Conference",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.arabicnlp-1.45/",
doi = "10.18653/v1/2024.arabicnlp-1.45",
pages = "467--472",
abstract = "Detecting propaganda in multimodal content, such as memes, is crucial for combating disinformation on social media. This paper presents a novel approach for the ArAIEval 2024 shared Task 2 on Multimodal Propagandistic Memes Classification, involving text, image, and multimodal classification of Arabic memes. For text classification (Task 2A), we fine-tune state-of-the-art Arabic language models and use ChatGPT4-generated synthetic text for data augmentation. For image classification (Task 2B), we fine-tune ResNet18, EfficientFormerV2, and ConvNeXt-tiny architectures with DALL-E-2-generated synthetic images. For multimodal classification (Task 2C), we combine ConvNeXt-tiny and BERT architectures in a fusion layer to enhance binary classification. Our results show significant performance improvements with data augmentation for text and image classification models and with the fusion layer for multimodal classification. We highlight challenges and opportunities for future research in multimodal propaganda detection in Arabic content, emphasizing the need for robust and adaptable models to combat disinformation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shah-etal-2024-mememind">
<titleInfo>
<title>MemeMind at ArAIEval Shared Task: Generative Augmentation and Feature Fusion for Multimodal Propaganda Detection in Arabic Memes through Advanced Language and Vision Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Uzair</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Rafiul</namePart>
<namePart type="family">Biswas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Agus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mowafa</namePart>
<namePart type="family">Househ</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>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Arabic Natural Language Processing Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</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">Ramy</namePart>
<namePart type="family">Eskander</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</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">Samia</namePart>
<namePart type="family">Touileb</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">Yaser</namePart>
<namePart type="family">Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</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">Hatem</namePart>
<namePart type="family">Haddad</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>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Detecting propaganda in multimodal content, such as memes, is crucial for combating disinformation on social media. This paper presents a novel approach for the ArAIEval 2024 shared Task 2 on Multimodal Propagandistic Memes Classification, involving text, image, and multimodal classification of Arabic memes. For text classification (Task 2A), we fine-tune state-of-the-art Arabic language models and use ChatGPT4-generated synthetic text for data augmentation. For image classification (Task 2B), we fine-tune ResNet18, EfficientFormerV2, and ConvNeXt-tiny architectures with DALL-E-2-generated synthetic images. For multimodal classification (Task 2C), we combine ConvNeXt-tiny and BERT architectures in a fusion layer to enhance binary classification. Our results show significant performance improvements with data augmentation for text and image classification models and with the fusion layer for multimodal classification. We highlight challenges and opportunities for future research in multimodal propaganda detection in Arabic content, emphasizing the need for robust and adaptable models to combat disinformation.</abstract>
<identifier type="citekey">shah-etal-2024-mememind</identifier>
<identifier type="doi">10.18653/v1/2024.arabicnlp-1.45</identifier>
<location>
<url>https://aclanthology.org/2024.arabicnlp-1.45/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>467</start>
<end>472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemeMind at ArAIEval Shared Task: Generative Augmentation and Feature Fusion for Multimodal Propaganda Detection in Arabic Memes through Advanced Language and Vision Models
%A Shah, Uzair
%A Biswas, Md. Rafiul
%A Agus, Marco
%A Househ, Mowafa
%A Zaghouani, Wajdi
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Eskander, Ramy
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Abdelali, Ahmed
%Y Touileb, Samia
%Y Hamed, Injy
%Y Onaizan, Yaser
%Y Alhafni, Bashar
%Y Antoun, Wissam
%Y Khalifa, Salam
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y AlKhamissi, Badr
%Y Almatham, Rawan
%Y Mrini, Khalil
%S Proceedings of the Second Arabic Natural Language Processing Conference
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F shah-etal-2024-mememind
%X Detecting propaganda in multimodal content, such as memes, is crucial for combating disinformation on social media. This paper presents a novel approach for the ArAIEval 2024 shared Task 2 on Multimodal Propagandistic Memes Classification, involving text, image, and multimodal classification of Arabic memes. For text classification (Task 2A), we fine-tune state-of-the-art Arabic language models and use ChatGPT4-generated synthetic text for data augmentation. For image classification (Task 2B), we fine-tune ResNet18, EfficientFormerV2, and ConvNeXt-tiny architectures with DALL-E-2-generated synthetic images. For multimodal classification (Task 2C), we combine ConvNeXt-tiny and BERT architectures in a fusion layer to enhance binary classification. Our results show significant performance improvements with data augmentation for text and image classification models and with the fusion layer for multimodal classification. We highlight challenges and opportunities for future research in multimodal propaganda detection in Arabic content, emphasizing the need for robust and adaptable models to combat disinformation.
%R 10.18653/v1/2024.arabicnlp-1.45
%U https://aclanthology.org/2024.arabicnlp-1.45/
%U https://doi.org/10.18653/v1/2024.arabicnlp-1.45
%P 467-472
Markdown (Informal)
[MemeMind at ArAIEval Shared Task: Generative Augmentation and Feature Fusion for Multimodal Propaganda Detection in Arabic Memes through Advanced Language and Vision Models](https://aclanthology.org/2024.arabicnlp-1.45/) (Shah et al., ArabicNLP 2024)
ACL