@inproceedings{hossain-etal-2022-combatant,
title = "{COMBATANT}@{T}amil{NLP}-{ACL}2022: Fine-grained Categorization of Abusive Comments using Logistic Regression",
author = "Hossain, Alamgir and
Bishal, Mahathir and
Hossain, Eftekhar and
Sharif, Omar and
Hoque, Mohammed Moshiul",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Krishnamurthy, Parameswari and
Sherly, Elizabeth and
Mahesan, Sinnathamby",
booktitle = "Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dravidianlangtech-1.34",
doi = "10.18653/v1/2022.dravidianlangtech-1.34",
pages = "221--228",
abstract = "With the widespread usage of social media and effortless internet access, millions of posts and comments are generated every minute. Unfortunately, with this substantial rise, the usage of abusive language has increased significantly in these mediums. This proliferation leads to many hazards such as cyber-bullying, vulgarity, online harassment and abuse. Therefore, it becomes a crucial issue to detect and mitigate the usage of abusive language. This work presents our system developed as part of the shared task to detect the abusive language in Tamil. We employed three machine learning (LR, DT, SVM), two deep learning (CNN+BiLSTM, CNN+BiLSTM with FastText) and a transformer-based model (Indic-BERT). The experimental results show that Logistic regression (LR) and CNN+BiLSTM models outperformed the others. Both Logistic Regression (LR) and CNN+BiLSTM with FastText achieved the weighted $F_1$-score of 0.39. However, LR obtained a higher recall value (0.44) than CNN+BiLSTM (0.36). This leads us to stand the $2^{nd}$ rank in the shared task competition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hossain-etal-2022-combatant">
<titleInfo>
<title>COMBATANT@TamilNLP-ACL2022: Fine-grained Categorization of Abusive Comments using Logistic Regression</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alamgir</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahathir</namePart>
<namePart type="family">Bishal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eftekhar</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Sharif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Speech 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">Parameswari</namePart>
<namePart type="family">Krishnamurthy</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">Sinnathamby</namePart>
<namePart type="family">Mahesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the widespread usage of social media and effortless internet access, millions of posts and comments are generated every minute. Unfortunately, with this substantial rise, the usage of abusive language has increased significantly in these mediums. This proliferation leads to many hazards such as cyber-bullying, vulgarity, online harassment and abuse. Therefore, it becomes a crucial issue to detect and mitigate the usage of abusive language. This work presents our system developed as part of the shared task to detect the abusive language in Tamil. We employed three machine learning (LR, DT, SVM), two deep learning (CNN+BiLSTM, CNN+BiLSTM with FastText) and a transformer-based model (Indic-BERT). The experimental results show that Logistic regression (LR) and CNN+BiLSTM models outperformed the others. Both Logistic Regression (LR) and CNN+BiLSTM with FastText achieved the weighted F₁-score of 0.39. However, LR obtained a higher recall value (0.44) than CNN+BiLSTM (0.36). This leads us to stand the 2ⁿd rank in the shared task competition.</abstract>
<identifier type="citekey">hossain-etal-2022-combatant</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.34</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.34</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>221</start>
<end>228</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T COMBATANT@TamilNLP-ACL2022: Fine-grained Categorization of Abusive Comments using Logistic Regression
%A Hossain, Alamgir
%A Bishal, Mahathir
%A Hossain, Eftekhar
%A Sharif, Omar
%A Hoque, Mohammed Moshiul
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%Y Mahesan, Sinnathamby
%S Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F hossain-etal-2022-combatant
%X With the widespread usage of social media and effortless internet access, millions of posts and comments are generated every minute. Unfortunately, with this substantial rise, the usage of abusive language has increased significantly in these mediums. This proliferation leads to many hazards such as cyber-bullying, vulgarity, online harassment and abuse. Therefore, it becomes a crucial issue to detect and mitigate the usage of abusive language. This work presents our system developed as part of the shared task to detect the abusive language in Tamil. We employed three machine learning (LR, DT, SVM), two deep learning (CNN+BiLSTM, CNN+BiLSTM with FastText) and a transformer-based model (Indic-BERT). The experimental results show that Logistic regression (LR) and CNN+BiLSTM models outperformed the others. Both Logistic Regression (LR) and CNN+BiLSTM with FastText achieved the weighted F₁-score of 0.39. However, LR obtained a higher recall value (0.44) than CNN+BiLSTM (0.36). This leads us to stand the 2ⁿd rank in the shared task competition.
%R 10.18653/v1/2022.dravidianlangtech-1.34
%U https://aclanthology.org/2022.dravidianlangtech-1.34
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.34
%P 221-228
Markdown (Informal)
[COMBATANT@TamilNLP-ACL2022: Fine-grained Categorization of Abusive Comments using Logistic Regression](https://aclanthology.org/2022.dravidianlangtech-1.34) (Hossain et al., DravidianLangTech 2022)
ACL