@inproceedings{naib-etal-2025-cuets,
title = "{CUET}{'}s{\_}{W}hite{\_}{W}alkers@{LT}-{EDI}-2025: A Multimodal Framework for the Detection of Misogynistic Memes in {C}hinese Online Content",
author = "Naib, Md. Mubasshir and
Rahman, Md. Mizanur and
Abrar, Jidan Al and
Hasan, Md. Mehedi and
Kawser, Md. Siddikul Imam 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-1.11/",
pages = "68--74",
ISBN = "978-88-6719-334-9",
abstract = "Memes, combining visual and textual elements, have emerged as a prominent medium for both expression and the spread of harmful ideologies, including misogyny. To address this issue in Chinese online content, we present a multimodal framework for misogyny meme detection as part of the LT-EDI@LDK 2025 Shared Task. Our study investigates a range of machine learning (ML) methods such as Logistic Regression, Support Vector Machines, and Random Forests, as well as deep learning (DL) architectures including CNNs and hybrid models like BiLSTM-CNN and CNN-GRU for extracting textual features. On the transformer side, we explored multiple pretrained models including mBERT, MuRIL, and BERT- base-chinese to capture nuanced language representations. These textual models were fused with visual features extracted from pretrained ResNet50 and DenseNet121 architectures using both early and decision-level fusion strategies. Among all evaluated configurations, the BERT-base-chinese + ResNet50 early fusion model achieved the best overall performance, with a macro F1-score of 0.8541, ranking 4th in the shared task. These findings underscore the effectiveness of combining pretrained vision and language models for tackling multimodal hate speech detection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="naib-etal-2025-cuets">
<titleInfo>
<title>CUET’s_White_Walkers@LT-EDI-2025: A Multimodal Framework for the Detection of Misogynistic Memes in Chinese Online Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mubasshir</namePart>
<namePart type="family">Naib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mizanur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jidan</namePart>
<namePart type="given">Al</namePart>
<namePart type="family">Abrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Mehedi</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Siddikul</namePart>
<namePart type="given">Imam</namePart>
<namePart type="family">Kawser</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>Memes, combining visual and textual elements, have emerged as a prominent medium for both expression and the spread of harmful ideologies, including misogyny. To address this issue in Chinese online content, we present a multimodal framework for misogyny meme detection as part of the LT-EDI@LDK 2025 Shared Task. Our study investigates a range of machine learning (ML) methods such as Logistic Regression, Support Vector Machines, and Random Forests, as well as deep learning (DL) architectures including CNNs and hybrid models like BiLSTM-CNN and CNN-GRU for extracting textual features. On the transformer side, we explored multiple pretrained models including mBERT, MuRIL, and BERT- base-chinese to capture nuanced language representations. These textual models were fused with visual features extracted from pretrained ResNet50 and DenseNet121 architectures using both early and decision-level fusion strategies. Among all evaluated configurations, the BERT-base-chinese + ResNet50 early fusion model achieved the best overall performance, with a macro F1-score of 0.8541, ranking 4th in the shared task. These findings underscore the effectiveness of combining pretrained vision and language models for tackling multimodal hate speech detection.</abstract>
<identifier type="citekey">naib-etal-2025-cuets</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.11/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>68</start>
<end>74</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET’s_White_Walkers@LT-EDI-2025: A Multimodal Framework for the Detection of Misogynistic Memes in Chinese Online Content
%A Naib, Md. Mubasshir
%A Rahman, Md. Mizanur
%A Abrar, Jidan Al
%A Hasan, Md. Mehedi
%A Kawser, Md. Siddikul Imam
%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 naib-etal-2025-cuets
%X Memes, combining visual and textual elements, have emerged as a prominent medium for both expression and the spread of harmful ideologies, including misogyny. To address this issue in Chinese online content, we present a multimodal framework for misogyny meme detection as part of the LT-EDI@LDK 2025 Shared Task. Our study investigates a range of machine learning (ML) methods such as Logistic Regression, Support Vector Machines, and Random Forests, as well as deep learning (DL) architectures including CNNs and hybrid models like BiLSTM-CNN and CNN-GRU for extracting textual features. On the transformer side, we explored multiple pretrained models including mBERT, MuRIL, and BERT- base-chinese to capture nuanced language representations. These textual models were fused with visual features extracted from pretrained ResNet50 and DenseNet121 architectures using both early and decision-level fusion strategies. Among all evaluated configurations, the BERT-base-chinese + ResNet50 early fusion model achieved the best overall performance, with a macro F1-score of 0.8541, ranking 4th in the shared task. These findings underscore the effectiveness of combining pretrained vision and language models for tackling multimodal hate speech detection.
%U https://aclanthology.org/2025.ltedi-1.11/
%P 68-74
Markdown (Informal)
[CUET’s_White_Walkers@LT-EDI-2025: A Multimodal Framework for the Detection of Misogynistic Memes in Chinese Online Content](https://aclanthology.org/2025.ltedi-1.11/) (Naib et al., LTEDI 2025)
ACL
- Md. Mubasshir Naib, Md. Mizanur Rahman, Jidan Al Abrar, Md. Mehedi Hasan, Md. Siddikul Imam Kawser, and Mohammad Shamsul Arefin. 2025. CUET’s_White_Walkers@LT-EDI-2025: A Multimodal Framework for the Detection of Misogynistic Memes in Chinese Online Content. In Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 68–74, Naples, Italy. Unior Press.