@inproceedings{mohiuddin-etal-2025-memeguard,
title = "{M}eme{G}uard: Transformer-Based Fusion for Multimodal Propaganda Detection in Low-Resource Social Media Memes",
author = "Mohiuddin, Md. and
Ahmed, Kawsar and
Ahsan, Shawly and
Hoque, Mohammed Moshiul",
editor = "Shukla, Ankita and
Kumar, Sandeep and
Bedi, Amrit Singh and
Chakraborty, Tanmoy",
booktitle = "Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.mmloso-1.4/",
pages = "35--47",
ISBN = "979-8-89176-311-1",
abstract = "Memes are now a common means of communication on social media. Their humor and short format help messages spread quickly and easily. Propagandistic memes use both words and images to influence opinions and behaviors, often appealing to emotions or ideologies. While propaganda detection has been well-studied in high-resource languages (HRLs), there has been a limited focus on low-resource languages (LRLs), such as Bengali. In this study, we introduce MemeGuard, a new dataset of 3,745 memes for detecting propaganda in Bengali. We tested more than 45 different methods, including both single and combined approaches with fusion. For text, BanglaBERT-1 achieved the best macro F1 score of 80.34{\%}, whereas the CLIP vision transformer scored 78.94{\%} for images. The proposed multimodal model, which combines BanglaBERT-2 and CLIP using Adaptive Modality Fusion, achieved the highest macro F1 score of 85.36{\%}. This work establishes a strong baseline and offers valuable insights for future research in Bengali multimodal content analysis."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohiuddin-etal-2025-memeguard">
<titleInfo>
<title>MemeGuard: Transformer-Based Fusion for Multimodal Propaganda Detection in Low-Resource Social Media Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="family">Mohiuddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kawsar</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shawly</namePart>
<namePart type="family">Ahsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankita</namePart>
<namePart type="family">Shukla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amrit</namePart>
<namePart type="given">Singh</namePart>
<namePart type="family">Bedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-311-1</identifier>
</relatedItem>
<abstract>Memes are now a common means of communication on social media. Their humor and short format help messages spread quickly and easily. Propagandistic memes use both words and images to influence opinions and behaviors, often appealing to emotions or ideologies. While propaganda detection has been well-studied in high-resource languages (HRLs), there has been a limited focus on low-resource languages (LRLs), such as Bengali. In this study, we introduce MemeGuard, a new dataset of 3,745 memes for detecting propaganda in Bengali. We tested more than 45 different methods, including both single and combined approaches with fusion. For text, BanglaBERT-1 achieved the best macro F1 score of 80.34%, whereas the CLIP vision transformer scored 78.94% for images. The proposed multimodal model, which combines BanglaBERT-2 and CLIP using Adaptive Modality Fusion, achieved the highest macro F1 score of 85.36%. This work establishes a strong baseline and offers valuable insights for future research in Bengali multimodal content analysis.</abstract>
<identifier type="citekey">mohiuddin-etal-2025-memeguard</identifier>
<location>
<url>https://aclanthology.org/2025.mmloso-1.4/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>35</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MemeGuard: Transformer-Based Fusion for Multimodal Propaganda Detection in Low-Resource Social Media Memes
%A Mohiuddin, Md.
%A Ahmed, Kawsar
%A Ahsan, Shawly
%A Hoque, Mohammed Moshiul
%Y Shukla, Ankita
%Y Kumar, Sandeep
%Y Bedi, Amrit Singh
%Y Chakraborty, Tanmoy
%S Proceedings of the 1st Workshop on Multimodal Models for Low-Resource Contexts and Social Impact (MMLoSo 2025)
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-311-1
%F mohiuddin-etal-2025-memeguard
%X Memes are now a common means of communication on social media. Their humor and short format help messages spread quickly and easily. Propagandistic memes use both words and images to influence opinions and behaviors, often appealing to emotions or ideologies. While propaganda detection has been well-studied in high-resource languages (HRLs), there has been a limited focus on low-resource languages (LRLs), such as Bengali. In this study, we introduce MemeGuard, a new dataset of 3,745 memes for detecting propaganda in Bengali. We tested more than 45 different methods, including both single and combined approaches with fusion. For text, BanglaBERT-1 achieved the best macro F1 score of 80.34%, whereas the CLIP vision transformer scored 78.94% for images. The proposed multimodal model, which combines BanglaBERT-2 and CLIP using Adaptive Modality Fusion, achieved the highest macro F1 score of 85.36%. This work establishes a strong baseline and offers valuable insights for future research in Bengali multimodal content analysis.
%U https://aclanthology.org/2025.mmloso-1.4/
%P 35-47
Markdown (Informal)
[MemeGuard: Transformer-Based Fusion for Multimodal Propaganda Detection in Low-Resource Social Media Memes](https://aclanthology.org/2025.mmloso-1.4/) (Mohiuddin et al., MMLoSo 2025)
ACL