@inproceedings{shanmugavadivel-etal-2025-kec-ai,
title = "{KEC}{\_}{AI}{\_}{GRYFFINDOR}@{D}ravidian{L}ang{T}ech 2025: Multimodal Hate Speech Detection in {D}ravidian languages",
author = "Shanmugavadivel, Kogilavani and
Subramanian, Malliga and
S, ShahidKhan and
Sashmitha.s, Shri and
S, Yashica",
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-1.31/",
doi = "10.18653/v1/2025.dravidianlangtech-1.31",
pages = "182--186",
ISBN = "979-8-89176-228-2",
abstract = "It is difficult to detect hate speech in codemixed Dravidian languages because the data is multilingual and unstructured. We took part in the shared task to detect hate speech in text and audio data for Tamil, Malayalam, and Telugu in this research. We tested different machine learning and deep learning models such as Logistic Regression, Ridge Classifier, Random Forest, and CNN. For Tamil, Logistic Regression gave the best macro-F1 score of 0.97 for text, whereas Ridge Classifier was the best for audio with a score of 0.75. For Malayalam, Random Forest gave the best F1-score of 0.97 for text, and CNN was the best for audio (F1 score: 0.69). For Telugu, Ridge Classifier gave the best F1-score of 0.89 for text, whereas CNN was the best for audio (F1-score: 0.87).Our findings prove that a multimodal solution effi ciently tackles the intricacy of hate speech detection in Dravidian languages. In this shared task,out of 145 teams we attained the 12th rank for Tamil and 7th rank for Malayalam and Telugu."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shanmugavadivel-etal-2025-kec-ai">
<titleInfo>
<title>KEC_AI_GRYFFINDOR@DravidianLangTech 2025: Multimodal Hate Speech Detection in Dravidian languages</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">ShahidKhan</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shri</namePart>
<namePart type="family">Sashmitha.s</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yashica</namePart>
<namePart type="family">S</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>It is difficult to detect hate speech in codemixed Dravidian languages because the data is multilingual and unstructured. We took part in the shared task to detect hate speech in text and audio data for Tamil, Malayalam, and Telugu in this research. We tested different machine learning and deep learning models such as Logistic Regression, Ridge Classifier, Random Forest, and CNN. For Tamil, Logistic Regression gave the best macro-F1 score of 0.97 for text, whereas Ridge Classifier was the best for audio with a score of 0.75. For Malayalam, Random Forest gave the best F1-score of 0.97 for text, and CNN was the best for audio (F1 score: 0.69). For Telugu, Ridge Classifier gave the best F1-score of 0.89 for text, whereas CNN was the best for audio (F1-score: 0.87).Our findings prove that a multimodal solution effi ciently tackles the intricacy of hate speech detection in Dravidian languages. In this shared task,out of 145 teams we attained the 12th rank for Tamil and 7th rank for Malayalam and Telugu.</abstract>
<identifier type="citekey">shanmugavadivel-etal-2025-kec-ai</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.31</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.31/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>182</start>
<end>186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KEC_AI_GRYFFINDOR@DravidianLangTech 2025: Multimodal Hate Speech Detection in Dravidian languages
%A Shanmugavadivel, Kogilavani
%A Subramanian, Malliga
%A S, ShahidKhan
%A Sashmitha.s, Shri
%A S, Yashica
%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-kec-ai
%X It is difficult to detect hate speech in codemixed Dravidian languages because the data is multilingual and unstructured. We took part in the shared task to detect hate speech in text and audio data for Tamil, Malayalam, and Telugu in this research. We tested different machine learning and deep learning models such as Logistic Regression, Ridge Classifier, Random Forest, and CNN. For Tamil, Logistic Regression gave the best macro-F1 score of 0.97 for text, whereas Ridge Classifier was the best for audio with a score of 0.75. For Malayalam, Random Forest gave the best F1-score of 0.97 for text, and CNN was the best for audio (F1 score: 0.69). For Telugu, Ridge Classifier gave the best F1-score of 0.89 for text, whereas CNN was the best for audio (F1-score: 0.87).Our findings prove that a multimodal solution effi ciently tackles the intricacy of hate speech detection in Dravidian languages. In this shared task,out of 145 teams we attained the 12th rank for Tamil and 7th rank for Malayalam and Telugu.
%R 10.18653/v1/2025.dravidianlangtech-1.31
%U https://aclanthology.org/2025.dravidianlangtech-1.31/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.31
%P 182-186
Markdown (Informal)
[KEC_AI_GRYFFINDOR@DravidianLangTech 2025: Multimodal Hate Speech Detection in Dravidian languages](https://aclanthology.org/2025.dravidianlangtech-1.31/) (Shanmugavadivel et al., DravidianLangTech 2025)
ACL
- Kogilavani Shanmugavadivel, Malliga Subramanian, ShahidKhan S, Shri Sashmitha.s, and Yashica S. 2025. KEC_AI_GRYFFINDOR@DravidianLangTech 2025: Multimodal Hate Speech Detection in Dravidian languages. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 182–186, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.