@inproceedings{bhuvana-etal-2025-ssntrio-dravidianlangtech-2025,
title = "{SSNT}rio @ {D}ravidian{L}ang{T}ech 2025: Hybrid Approach for Hate Speech Detection in {D}ravidian Languages with Text and Audio Modalities",
author = "Bhuvana, J and
T T, Mirnalinee and
R, Rohan and
Seshan, Diya and
Koushik, Avaneesh",
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-1.80/",
doi = "10.18653/v1/2025.dravidianlangtech-1.80",
pages = "454--458",
ISBN = "979-8-89176-228-2",
abstract = "This paper presents the approach and findings from the Multimodal Social Media Data Analysis in Dravidian Languages (MSMDA-DL) shared task at DravidianLangTech@NAACL 2025. The task focuses on detecting multimodal hate speech in Tamil, Malayalam, and Telugu, requiring models to analyze both text and speech components from social media content. The proposed methodology uses language-specific BERT models for the provided text transcripts, followed by multimodal feature extraction techniques, and classification using a Random Forest classifier to enhance performance across the three languages. The models achieved a macro-F1 score of 0.7332 (Rank 1) in Tamil, 0.7511 (Rank 1) in Malayalam, and 0.3758 (Rank 2) in Telugu, demonstrating the effectiveness of the approach in multilingual settings. The models performed well despite the challenges posed by limited resources, highlighting the potential of language-specific BERT models and multimodal techniques in hate speech detection for Dravidian languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhuvana-etal-2025-ssntrio-dravidianlangtech-2025">
<titleInfo>
<title>SSNTrio @ DravidianLangTech 2025: Hybrid Approach for Hate Speech Detection in Dravidian Languages with Text and Audio Modalities</title>
</titleInfo>
<name type="personal">
<namePart type="given">J</namePart>
<namePart type="family">Bhuvana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirnalinee</namePart>
<namePart type="family">T T</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rohan</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diya</namePart>
<namePart type="family">Seshan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avaneesh</namePart>
<namePart type="family">Koushik</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>This paper presents the approach and findings from the Multimodal Social Media Data Analysis in Dravidian Languages (MSMDA-DL) shared task at DravidianLangTech@NAACL 2025. The task focuses on detecting multimodal hate speech in Tamil, Malayalam, and Telugu, requiring models to analyze both text and speech components from social media content. The proposed methodology uses language-specific BERT models for the provided text transcripts, followed by multimodal feature extraction techniques, and classification using a Random Forest classifier to enhance performance across the three languages. The models achieved a macro-F1 score of 0.7332 (Rank 1) in Tamil, 0.7511 (Rank 1) in Malayalam, and 0.3758 (Rank 2) in Telugu, demonstrating the effectiveness of the approach in multilingual settings. The models performed well despite the challenges posed by limited resources, highlighting the potential of language-specific BERT models and multimodal techniques in hate speech detection for Dravidian languages.</abstract>
<identifier type="citekey">bhuvana-etal-2025-ssntrio-dravidianlangtech-2025</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.80</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.80/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>454</start>
<end>458</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SSNTrio @ DravidianLangTech 2025: Hybrid Approach for Hate Speech Detection in Dravidian Languages with Text and Audio Modalities
%A Bhuvana, J.
%A T T, Mirnalinee
%A R, Rohan
%A Seshan, Diya
%A Koushik, Avaneesh
%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 bhuvana-etal-2025-ssntrio-dravidianlangtech-2025
%X This paper presents the approach and findings from the Multimodal Social Media Data Analysis in Dravidian Languages (MSMDA-DL) shared task at DravidianLangTech@NAACL 2025. The task focuses on detecting multimodal hate speech in Tamil, Malayalam, and Telugu, requiring models to analyze both text and speech components from social media content. The proposed methodology uses language-specific BERT models for the provided text transcripts, followed by multimodal feature extraction techniques, and classification using a Random Forest classifier to enhance performance across the three languages. The models achieved a macro-F1 score of 0.7332 (Rank 1) in Tamil, 0.7511 (Rank 1) in Malayalam, and 0.3758 (Rank 2) in Telugu, demonstrating the effectiveness of the approach in multilingual settings. The models performed well despite the challenges posed by limited resources, highlighting the potential of language-specific BERT models and multimodal techniques in hate speech detection for Dravidian languages.
%R 10.18653/v1/2025.dravidianlangtech-1.80
%U https://aclanthology.org/2025.dravidianlangtech-1.80/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.80
%P 454-458
Markdown (Informal)
[SSNTrio @ DravidianLangTech 2025: Hybrid Approach for Hate Speech Detection in Dravidian Languages with Text and Audio Modalities](https://aclanthology.org/2025.dravidianlangtech-1.80/) (Bhuvana et al., DravidianLangTech 2025)
ACL
- J Bhuvana, Mirnalinee T T, Rohan R, Diya Seshan, and Avaneesh Koushik. 2025. SSNTrio @ DravidianLangTech 2025: Hybrid Approach for Hate Speech Detection in Dravidian Languages with Text and Audio Modalities. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 454–458, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.