@inproceedings{shanmugavadivel-etal-2025-innovationengineers,
title = "{I}nnovation{E}ngineers@{D}ravidian{L}ang{T}ech 2025: Enhanced {CNN} Models for Detecting Misogyny in {T}amil Memes Using Image and Text Classification",
author = "Shanmugavadivel, Kogilavani and
Subramanian, Malliga and
M, Pooja Sree and
V, Palanimurugan and
K, Roshini Priya",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Rajiakodi, Saranya and
Palani, Balasubramanian and
Subramanian, Malliga and
Cn, Subalalitha and
Chinnappa, Dhivya",
booktitle = "Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = may,
year = "2025",
address = "Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.dravidianlangtech-1.27/",
doi = "10.18653/v1/2025.dravidianlangtech-1.27",
pages = "162--166",
ISBN = "979-8-89176-228-2",
abstract = "The rise of misogynistic memes on social media posed challenges to civil discourse. This paper aimed to detect misogyny in Dravidian language memes using a multimodal deep learning approach. We integrated Bidirectional Encoder Representations from Transformers (BERT), Long Short-Term Memory (LSTM), EfficientNet, and a Vision Language Model (VLM) to analyze textual and visual informa tion. EfficientNet extracted image features, LSTM captured sequential text patterns, and BERT learned language-specific embeddings. Among these, VLM achieved the highest accuracy of 85.0{\%} and an F1-score of 70.8, effectively capturing visual-textual relationships. Validated on a curated dataset, our method outperformed baselines in precision, recall, and F1-score. Our approach ranked 12th out of 118 participants for the Tamil language, highlighting its competitive performance. This research emphasizes the importance of multimodal models in detecting harmful content. Future work can explore improved feature fusion techniques to enhance classification accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shanmugavadivel-etal-2025-innovationengineers">
<titleInfo>
<title>InnovationEngineers@DravidianLangTech 2025: Enhanced CNN Models for Detecting Misogyny in Tamil Memes Using Image and Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kogilavani</namePart>
<namePart type="family">Shanmugavadivel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pooja</namePart>
<namePart type="given">Sree</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Palanimurugan</namePart>
<namePart type="family">V</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roshini</namePart>
<namePart type="given">Priya</namePart>
<namePart type="family">K</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-228-2</identifier>
</relatedItem>
<abstract>The rise of misogynistic memes on social media posed challenges to civil discourse. This paper aimed to detect misogyny in Dravidian language memes using a multimodal deep learning approach. We integrated Bidirectional Encoder Representations from Transformers (BERT), Long Short-Term Memory (LSTM), EfficientNet, and a Vision Language Model (VLM) to analyze textual and visual informa tion. EfficientNet extracted image features, LSTM captured sequential text patterns, and BERT learned language-specific embeddings. Among these, VLM achieved the highest accuracy of 85.0% and an F1-score of 70.8, effectively capturing visual-textual relationships. Validated on a curated dataset, our method outperformed baselines in precision, recall, and F1-score. Our approach ranked 12th out of 118 participants for the Tamil language, highlighting its competitive performance. This research emphasizes the importance of multimodal models in detecting harmful content. Future work can explore improved feature fusion techniques to enhance classification accuracy.</abstract>
<identifier type="citekey">shanmugavadivel-etal-2025-innovationengineers</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.27</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.27/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>162</start>
<end>166</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T InnovationEngineers@DravidianLangTech 2025: Enhanced CNN Models for Detecting Misogyny in Tamil Memes Using Image and Text Classification
%A Shanmugavadivel, Kogilavani
%A Subramanian, Malliga
%A M, Pooja Sree
%A V, Palanimurugan
%A K, Roshini Priya
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Rajiakodi, Saranya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Cn, Subalalitha
%Y Chinnappa, Dhivya
%S Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2025
%8 May
%I Association for Computational Linguistics
%C Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico
%@ 979-8-89176-228-2
%F shanmugavadivel-etal-2025-innovationengineers
%X The rise of misogynistic memes on social media posed challenges to civil discourse. This paper aimed to detect misogyny in Dravidian language memes using a multimodal deep learning approach. We integrated Bidirectional Encoder Representations from Transformers (BERT), Long Short-Term Memory (LSTM), EfficientNet, and a Vision Language Model (VLM) to analyze textual and visual informa tion. EfficientNet extracted image features, LSTM captured sequential text patterns, and BERT learned language-specific embeddings. Among these, VLM achieved the highest accuracy of 85.0% and an F1-score of 70.8, effectively capturing visual-textual relationships. Validated on a curated dataset, our method outperformed baselines in precision, recall, and F1-score. Our approach ranked 12th out of 118 participants for the Tamil language, highlighting its competitive performance. This research emphasizes the importance of multimodal models in detecting harmful content. Future work can explore improved feature fusion techniques to enhance classification accuracy.
%R 10.18653/v1/2025.dravidianlangtech-1.27
%U https://aclanthology.org/2025.dravidianlangtech-1.27/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.27
%P 162-166
Markdown (Informal)
[InnovationEngineers@DravidianLangTech 2025: Enhanced CNN Models for Detecting Misogyny in Tamil Memes Using Image and Text Classification](https://aclanthology.org/2025.dravidianlangtech-1.27/) (Shanmugavadivel et al., DravidianLangTech 2025)
ACL
- Kogilavani Shanmugavadivel, Malliga Subramanian, Pooja Sree M, Palanimurugan V, and Roshini Priya K. 2025. InnovationEngineers@DravidianLangTech 2025: Enhanced CNN Models for Detecting Misogyny in Tamil Memes Using Image and Text Classification. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 162–166, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.