@inproceedings{faisal-etal-2025-team-luminaries,
title = "{T}eam{\_}{L}uminaries{\_}0227@{LT}-{EDI}-2025: A Transformer-Based Fusion Approach to Misogyny Detection in {C}hinese Memes",
author = "Faisal, Adnan and
Chowdhury, Shiti and
Labib, Momtazul Arefin and
Murad, Hasan",
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-1.20/",
pages = "116--120",
ISBN = "978-88-6719-334-9",
abstract = "Memes, originally crafted for humor or cultural commentary, have evolved into powerful tools for spreading harmful content, particularly misogynistic ideologies. These memes sustain damaging gender stereotypes, further entrenching social inequality and encouraging toxic behavior across online platforms. While progress has been made in detecting harmful memes in English, identifying misogynistic content in Chinese remains challenging due to the language{'}s complexities and cultural subtleties. The multimodal nature of memes, combining text and images, adds to the detection difficulty. In the LT-EDI@LDK 2025 Shared Task on Misogyny Meme Detection, we have focused on analyzing both text and image elements to identify misogynistic content in Chinese memes. For text-based models, we have experimented with Chinese BERT, XLM-RoBERTa and DistilBERT, with Chinese BERT yielding the highest performance, achieving an F1 score of 0.86. In terms of image models, VGG16 outperformed ResNet and ViT, also achieving an F1 score of 0.85. Among all model combinations, the integration of Chinese BERT with VGG16 emerged as the most impactful, delivering superior performance, highlighting the benefit of a multimodal approach. By exploiting these two modalities, our model has effectively captured the subtle details present in memes, improving its ability to accurately detect misogynistic content. This approach has resulted in a macro F1 score of 0.90355, securing 3rd rank in the task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faisal-etal-2025-team-luminaries">
<titleInfo>
<title>Team_Luminaries_0227@LT-EDI-2025: A Transformer-Based Fusion Approach to Misogyny Detection in Chinese Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adnan</namePart>
<namePart type="family">Faisal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiti</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Momtazul</namePart>
<namePart type="given">Arefin</namePart>
<namePart type="family">Labib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Murad</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>Memes, originally crafted for humor or cultural commentary, have evolved into powerful tools for spreading harmful content, particularly misogynistic ideologies. These memes sustain damaging gender stereotypes, further entrenching social inequality and encouraging toxic behavior across online platforms. While progress has been made in detecting harmful memes in English, identifying misogynistic content in Chinese remains challenging due to the language’s complexities and cultural subtleties. The multimodal nature of memes, combining text and images, adds to the detection difficulty. In the LT-EDI@LDK 2025 Shared Task on Misogyny Meme Detection, we have focused on analyzing both text and image elements to identify misogynistic content in Chinese memes. For text-based models, we have experimented with Chinese BERT, XLM-RoBERTa and DistilBERT, with Chinese BERT yielding the highest performance, achieving an F1 score of 0.86. In terms of image models, VGG16 outperformed ResNet and ViT, also achieving an F1 score of 0.85. Among all model combinations, the integration of Chinese BERT with VGG16 emerged as the most impactful, delivering superior performance, highlighting the benefit of a multimodal approach. By exploiting these two modalities, our model has effectively captured the subtle details present in memes, improving its ability to accurately detect misogynistic content. This approach has resulted in a macro F1 score of 0.90355, securing 3rd rank in the task.</abstract>
<identifier type="citekey">faisal-etal-2025-team-luminaries</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.20/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>116</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team_Luminaries_0227@LT-EDI-2025: A Transformer-Based Fusion Approach to Misogyny Detection in Chinese Memes
%A Faisal, Adnan
%A Chowdhury, Shiti
%A Labib, Momtazul Arefin
%A Murad, Hasan
%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 faisal-etal-2025-team-luminaries
%X Memes, originally crafted for humor or cultural commentary, have evolved into powerful tools for spreading harmful content, particularly misogynistic ideologies. These memes sustain damaging gender stereotypes, further entrenching social inequality and encouraging toxic behavior across online platforms. While progress has been made in detecting harmful memes in English, identifying misogynistic content in Chinese remains challenging due to the language’s complexities and cultural subtleties. The multimodal nature of memes, combining text and images, adds to the detection difficulty. In the LT-EDI@LDK 2025 Shared Task on Misogyny Meme Detection, we have focused on analyzing both text and image elements to identify misogynistic content in Chinese memes. For text-based models, we have experimented with Chinese BERT, XLM-RoBERTa and DistilBERT, with Chinese BERT yielding the highest performance, achieving an F1 score of 0.86. In terms of image models, VGG16 outperformed ResNet and ViT, also achieving an F1 score of 0.85. Among all model combinations, the integration of Chinese BERT with VGG16 emerged as the most impactful, delivering superior performance, highlighting the benefit of a multimodal approach. By exploiting these two modalities, our model has effectively captured the subtle details present in memes, improving its ability to accurately detect misogynistic content. This approach has resulted in a macro F1 score of 0.90355, securing 3rd rank in the task.
%U https://aclanthology.org/2025.ltedi-1.20/
%P 116-120
Markdown (Informal)
[Team_Luminaries_0227@LT-EDI-2025: A Transformer-Based Fusion Approach to Misogyny Detection in Chinese Memes](https://aclanthology.org/2025.ltedi-1.20/) (Faisal et al., LTEDI 2025)
ACL