@inproceedings{s-n-etal-2022-cen,
title = "{CEN}-{T}amil@{D}ravidian{L}ang{T}ech-{ACL}2022: Abusive Comment detection in {T}amil using {TF}-{IDF} and Random Kitchen Sink Algorithm",
author = "S N, Prasanth and
Aswin Raj, R and
P, Adhithan and
B, Premjith and
Kp, Soman",
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-1.11",
doi = "10.18653/v1/2022.dravidianlangtech-1.11",
pages = "70--74",
abstract = "This paper describes the approach of team CEN-Tamil used for abusive comment detection in Tamil. This task aims to identify whether a given comment contains abusive comments. We used TF-IDF with char-wb analyzers with Random Kitchen Sink (RKS) algorithm to create feature vectors and the Support Vector Machine (SVM) classifier with polynomial kernel for classification. We used this method for both Tamil and Tamil-English datasets and secured first place with an f1-score of 0.32 and seventh place with an f1-score of 0.25, respectively. The code for our approach is shared in the GitHub repository.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="s-n-etal-2022-cen">
<titleInfo>
<title>CEN-Tamil@DravidianLangTech-ACL2022: Abusive Comment detection in Tamil using TF-IDF and Random Kitchen Sink Algorithm</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prasanth</namePart>
<namePart type="family">S N</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">R</namePart>
<namePart type="family">Aswin Raj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adhithan</namePart>
<namePart type="family">P</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Premjith</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soman</namePart>
<namePart type="family">Kp</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>This paper describes the approach of team CEN-Tamil used for abusive comment detection in Tamil. This task aims to identify whether a given comment contains abusive comments. We used TF-IDF with char-wb analyzers with Random Kitchen Sink (RKS) algorithm to create feature vectors and the Support Vector Machine (SVM) classifier with polynomial kernel for classification. We used this method for both Tamil and Tamil-English datasets and secured first place with an f1-score of 0.32 and seventh place with an f1-score of 0.25, respectively. The code for our approach is shared in the GitHub repository.</abstract>
<identifier type="citekey">s-n-etal-2022-cen</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.11</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.11</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>70</start>
<end>74</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CEN-Tamil@DravidianLangTech-ACL2022: Abusive Comment detection in Tamil using TF-IDF and Random Kitchen Sink Algorithm
%A S N, Prasanth
%A Aswin Raj, R.
%A P, Adhithan
%A B, Premjith
%A Kp, Soman
%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 s-n-etal-2022-cen
%X This paper describes the approach of team CEN-Tamil used for abusive comment detection in Tamil. This task aims to identify whether a given comment contains abusive comments. We used TF-IDF with char-wb analyzers with Random Kitchen Sink (RKS) algorithm to create feature vectors and the Support Vector Machine (SVM) classifier with polynomial kernel for classification. We used this method for both Tamil and Tamil-English datasets and secured first place with an f1-score of 0.32 and seventh place with an f1-score of 0.25, respectively. The code for our approach is shared in the GitHub repository.
%R 10.18653/v1/2022.dravidianlangtech-1.11
%U https://aclanthology.org/2022.dravidianlangtech-1.11
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.11
%P 70-74
Markdown (Informal)
[CEN-Tamil@DravidianLangTech-ACL2022: Abusive Comment detection in Tamil using TF-IDF and Random Kitchen Sink Algorithm](https://aclanthology.org/2022.dravidianlangtech-1.11) (S N et al., DravidianLangTech 2022)
ACL