@inproceedings{rahman-etal-2025-cuet-ignite,
title = "{CUET}{\_}{I}gnite@{LT}-{EDI}-2025: A Multimodal Transformer-Based Approach for Detecting Misogynistic Memes in {C}hinese Social Media",
author = "Rahman, Md. Mahadi and
Uddin, Mohammad Minhaj and
Oman, Mohammad and
Arefin, Mohammad Shamsul",
editor = "Gkirtzou, Katerina and
{\v{Z}}itnik, Slavko and
Gracia, Jorge and
Gromann, Dagmar and
di Buono, Maria Pia and
Monti, Johanna and
Ionov, Maxim",
booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = sep,
year = "2025",
address = "Naples, Italy",
publisher = "Unior Press",
url = "https://aclanthology.org/2025.ltedi-1.28/",
pages = "172--177",
ISBN = "978-88-6719-334-9",
abstract = "Misogynistic content in memes on social me dia platforms poses a significant challenge for content moderation, particularly in languages like Chinese, where cultural nuances and multi modal elements complicate detection. Address ing this issue is critical for creating safer online environments, A shared task on multimodal misogyny identification in Chinese memes, or ganized by LT-EDI@LDK 2025, provided a curated dataset for this purpose. Since memes mix pictures and words, we used two smart tools: ResNet-50 to understand the images and Chinese RoBERTa to make sense of the text. The data set consisted of Chinese social media memes annotated with binary labels (Misogynistic and Non-Misogynistic), capturing explicit misogyny, implicit biases, and stereo types. Our experiments demonstrated that ResNet-50 combined with Chinese RoBERTa achieved a macro F1 score of 0.91, placing second in the competition and underscoring its effectiveness in handling the complex interplay of text and visuals in Chinese memes. This research advances multimodal misogyny detection and contributes to natural language and vision processing for low-resource languages, particularly in combating gender-based abuse online."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rahman-etal-2025-cuet-ignite">
<titleInfo>
<title>CUET_Ignite@LT-EDI-2025: A Multimodal Transformer-Based Approach for Detecting Misogynistic Memes in Chinese Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mahadi</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Minhaj</namePart>
<namePart type="family">Uddin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Oman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Shamsul</namePart>
<namePart type="family">Arefin</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 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slavko</namePart>
<namePart type="family">Žitnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gracia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Pia</namePart>
<namePart type="family">di Buono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Unior Press</publisher>
<place>
<placeTerm type="text">Naples, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-88-6719-334-9</identifier>
</relatedItem>
<abstract>Misogynistic content in memes on social me dia platforms poses a significant challenge for content moderation, particularly in languages like Chinese, where cultural nuances and multi modal elements complicate detection. Address ing this issue is critical for creating safer online environments, A shared task on multimodal misogyny identification in Chinese memes, or ganized by LT-EDI@LDK 2025, provided a curated dataset for this purpose. Since memes mix pictures and words, we used two smart tools: ResNet-50 to understand the images and Chinese RoBERTa to make sense of the text. The data set consisted of Chinese social media memes annotated with binary labels (Misogynistic and Non-Misogynistic), capturing explicit misogyny, implicit biases, and stereo types. Our experiments demonstrated that ResNet-50 combined with Chinese RoBERTa achieved a macro F1 score of 0.91, placing second in the competition and underscoring its effectiveness in handling the complex interplay of text and visuals in Chinese memes. This research advances multimodal misogyny detection and contributes to natural language and vision processing for low-resource languages, particularly in combating gender-based abuse online.</abstract>
<identifier type="citekey">rahman-etal-2025-cuet-ignite</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.28/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>172</start>
<end>177</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET_Ignite@LT-EDI-2025: A Multimodal Transformer-Based Approach for Detecting Misogynistic Memes in Chinese Social Media
%A Rahman, Md. Mahadi
%A Uddin, Mohammad Minhaj
%A Oman, Mohammad
%A Arefin, Mohammad Shamsul
%Y Gkirtzou, Katerina
%Y Žitnik, Slavko
%Y Gracia, Jorge
%Y Gromann, Dagmar
%Y di Buono, Maria Pia
%Y Monti, Johanna
%Y Ionov, Maxim
%S Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2025
%8 September
%I Unior Press
%C Naples, Italy
%@ 978-88-6719-334-9
%F rahman-etal-2025-cuet-ignite
%X Misogynistic content in memes on social me dia platforms poses a significant challenge for content moderation, particularly in languages like Chinese, where cultural nuances and multi modal elements complicate detection. Address ing this issue is critical for creating safer online environments, A shared task on multimodal misogyny identification in Chinese memes, or ganized by LT-EDI@LDK 2025, provided a curated dataset for this purpose. Since memes mix pictures and words, we used two smart tools: ResNet-50 to understand the images and Chinese RoBERTa to make sense of the text. The data set consisted of Chinese social media memes annotated with binary labels (Misogynistic and Non-Misogynistic), capturing explicit misogyny, implicit biases, and stereo types. Our experiments demonstrated that ResNet-50 combined with Chinese RoBERTa achieved a macro F1 score of 0.91, placing second in the competition and underscoring its effectiveness in handling the complex interplay of text and visuals in Chinese memes. This research advances multimodal misogyny detection and contributes to natural language and vision processing for low-resource languages, particularly in combating gender-based abuse online.
%U https://aclanthology.org/2025.ltedi-1.28/
%P 172-177
Markdown (Informal)
[CUET_Ignite@LT-EDI-2025: A Multimodal Transformer-Based Approach for Detecting Misogynistic Memes in Chinese Social Media](https://aclanthology.org/2025.ltedi-1.28/) (Rahman et al., LTEDI 2025)
ACL