@inproceedings{s-etal-2025-ansr,
title = "{ANSR}@{D}ravidian{L}ang{T}ech 2025: Detection of Abusive {T}amil and {M}alayalam Text Targeting Women on Social Media using {R}o{BERT}a and {XGB}oost",
author = "S, Nishanth and
Rengarajan, Shruthi and
Ananthasivan, S and
Rahul, Burugu and
S, Sachin Kumar",
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-1.121/",
doi = "10.18653/v1/2025.dravidianlangtech-1.121",
pages = "711--715",
ISBN = "979-8-89176-228-2",
abstract = "Abusive language directed at women on social media, often characterized by crude slang, offensive terms, and profanity, is not just harmful communication but also acts as a tool for serious and widespread cyber violence. It is imperative that this pressing issue be addressed in order to establish safer online spaces and provide efficient methods for detecting and minimising this kind of abuse. However, the intentional masking of abusive language, especially in regional languages like Tamil and Malayalam, presents significant obstacles, making detection and prevention more difficult. The system created effectively identifies abusive sentences using supervised machine learning techniques based on RoBerta embeddings. The method aims to improve upon the current abusive language detection systems, which are essential for various online platforms, including social media and online gaming services. The proposed method currently ranked 8 in malayalam and 20 in tamil in terms of f1 score."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="s-etal-2025-ansr">
<titleInfo>
<title>ANSR@DravidianLangTech 2025: Detection of Abusive Tamil and Malayalam Text Targeting Women on Social Media using RoBERTa and XGBoost</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nishanth</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruthi</namePart>
<namePart type="family">Rengarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">S</namePart>
<namePart type="family">Ananthasivan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burugu</namePart>
<namePart type="family">Rahul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="given">Kumar</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>Abusive language directed at women on social media, often characterized by crude slang, offensive terms, and profanity, is not just harmful communication but also acts as a tool for serious and widespread cyber violence. It is imperative that this pressing issue be addressed in order to establish safer online spaces and provide efficient methods for detecting and minimising this kind of abuse. However, the intentional masking of abusive language, especially in regional languages like Tamil and Malayalam, presents significant obstacles, making detection and prevention more difficult. The system created effectively identifies abusive sentences using supervised machine learning techniques based on RoBerta embeddings. The method aims to improve upon the current abusive language detection systems, which are essential for various online platforms, including social media and online gaming services. The proposed method currently ranked 8 in malayalam and 20 in tamil in terms of f1 score.</abstract>
<identifier type="citekey">s-etal-2025-ansr</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.121</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.121/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>711</start>
<end>715</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ANSR@DravidianLangTech 2025: Detection of Abusive Tamil and Malayalam Text Targeting Women on Social Media using RoBERTa and XGBoost
%A S, Nishanth
%A Rengarajan, Shruthi
%A Ananthasivan, S.
%A Rahul, Burugu
%A S, Sachin Kumar
%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 s-etal-2025-ansr
%X Abusive language directed at women on social media, often characterized by crude slang, offensive terms, and profanity, is not just harmful communication but also acts as a tool for serious and widespread cyber violence. It is imperative that this pressing issue be addressed in order to establish safer online spaces and provide efficient methods for detecting and minimising this kind of abuse. However, the intentional masking of abusive language, especially in regional languages like Tamil and Malayalam, presents significant obstacles, making detection and prevention more difficult. The system created effectively identifies abusive sentences using supervised machine learning techniques based on RoBerta embeddings. The method aims to improve upon the current abusive language detection systems, which are essential for various online platforms, including social media and online gaming services. The proposed method currently ranked 8 in malayalam and 20 in tamil in terms of f1 score.
%R 10.18653/v1/2025.dravidianlangtech-1.121
%U https://aclanthology.org/2025.dravidianlangtech-1.121/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.121
%P 711-715
Markdown (Informal)
[ANSR@DravidianLangTech 2025: Detection of Abusive Tamil and Malayalam Text Targeting Women on Social Media using RoBERTa and XGBoost](https://aclanthology.org/2025.dravidianlangtech-1.121/) (S et al., DravidianLangTech 2025)
ACL
- Nishanth S, Shruthi Rengarajan, S Ananthasivan, Burugu Rahul, and Sachin Kumar S. 2025. ANSR@DravidianLangTech 2025: Detection of Abusive Tamil and Malayalam Text Targeting Women on Social Media using RoBERTa and XGBoost. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 711–715, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.