@inproceedings{johnson-etal-2025-rmkmavericks,
title = "{RMKM}avericks@{D}ravidian{L}ang{T}ech 2025: Tackling Abusive {T}amil and {M}alayalam Text Targeting Women: A Linguistic Approach",
author = "Johnson, Sandra and
E, Boomika and
P, Lahari",
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-1.4/",
doi = "10.18653/v1/2025.dravidianlangtech-1.4",
pages = "19--23",
ISBN = "979-8-89176-228-2",
abstract = "Social media abuse of women is a widespread problem, especially in regional languages like Tamil and Malayalam, where there are few tools for automated identification. The use of machine learning methods to detect abusive messages in several languages is examined in this work. An external dataset was used to train a Support Vector Machine (SVM) model for Tamil, which produced an F1 score of 0.6196. Using the given dataset, a Multinomial Naive Bayes (MNB) model was trained for Malayalam, obtaining an F1 score of 0.6484. Both models processed and analyzed textual input efficiently by using TF-IDF vectorization for feature extraction. This method shows the ability to solve the linguistic diversity and complexity of abusive language identification by utilizing language-specific datasets and customized algorithms. The results highlight how crucial it is to use focused machine learning techniques to make online spaces safer for women, especially when speaking minority languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johnson-etal-2025-rmkmavericks">
<titleInfo>
<title>RMKMavericks@DravidianLangTech 2025: Tackling Abusive Tamil and Malayalam Text Targeting Women: A Linguistic Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boomika</namePart>
<namePart type="family">E</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lahari</namePart>
<namePart type="family">P</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>Social media abuse of women is a widespread problem, especially in regional languages like Tamil and Malayalam, where there are few tools for automated identification. The use of machine learning methods to detect abusive messages in several languages is examined in this work. An external dataset was used to train a Support Vector Machine (SVM) model for Tamil, which produced an F1 score of 0.6196. Using the given dataset, a Multinomial Naive Bayes (MNB) model was trained for Malayalam, obtaining an F1 score of 0.6484. Both models processed and analyzed textual input efficiently by using TF-IDF vectorization for feature extraction. This method shows the ability to solve the linguistic diversity and complexity of abusive language identification by utilizing language-specific datasets and customized algorithms. The results highlight how crucial it is to use focused machine learning techniques to make online spaces safer for women, especially when speaking minority languages.</abstract>
<identifier type="citekey">johnson-etal-2025-rmkmavericks</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.4</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.4/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>19</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RMKMavericks@DravidianLangTech 2025: Tackling Abusive Tamil and Malayalam Text Targeting Women: A Linguistic Approach
%A Johnson, Sandra
%A E, Boomika
%A P, Lahari
%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 johnson-etal-2025-rmkmavericks
%X Social media abuse of women is a widespread problem, especially in regional languages like Tamil and Malayalam, where there are few tools for automated identification. The use of machine learning methods to detect abusive messages in several languages is examined in this work. An external dataset was used to train a Support Vector Machine (SVM) model for Tamil, which produced an F1 score of 0.6196. Using the given dataset, a Multinomial Naive Bayes (MNB) model was trained for Malayalam, obtaining an F1 score of 0.6484. Both models processed and analyzed textual input efficiently by using TF-IDF vectorization for feature extraction. This method shows the ability to solve the linguistic diversity and complexity of abusive language identification by utilizing language-specific datasets and customized algorithms. The results highlight how crucial it is to use focused machine learning techniques to make online spaces safer for women, especially when speaking minority languages.
%R 10.18653/v1/2025.dravidianlangtech-1.4
%U https://aclanthology.org/2025.dravidianlangtech-1.4/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.4
%P 19-23
Markdown (Informal)
[RMKMavericks@DravidianLangTech 2025: Tackling Abusive Tamil and Malayalam Text Targeting Women: A Linguistic Approach](https://aclanthology.org/2025.dravidianlangtech-1.4/) (Johnson et al., DravidianLangTech 2025)
ACL