@inproceedings{saumya-etal-2021-offensive,
title = "Offensive language identification in {D}ravidian code mixed social media text",
author = "Saumya, Sunil and
Kumar, Abhinav and
Singh, Jyoti Prakash",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Kumar M, Anand and
Krishnamurthy, Parameswari and
Sherly, Elizabeth",
booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
month = apr,
year = "2021",
address = "Kyiv",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dravidianlangtech-1.5",
pages = "36--45",
abstract = "Hate speech and offensive language recognition in social media platforms have been an active field of research over recent years. In non-native English spoken countries, social media texts are mostly in code mixed or script mixed/switched form. The current study presents extensive experiments using multiple machine learning, deep learning, and transfer learning models to detect offensive content on Twitter. The data set used for this study are in Tanglish (Tamil and English), Manglish (Malayalam and English) code-mixed, and Malayalam script-mixed. The experimental results showed that 1 to 6-gram character TF-IDF features are better for the said task. The best performing models were naive bayes, logistic regression, and vanilla neural network for the dataset Tamil code-mix, Malayalam code-mixed, and Malayalam script-mixed, respectively instead of more popular transfer learning models such as BERT and ULMFiT and hybrid deep models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saumya-etal-2021-offensive">
<titleInfo>
<title>Offensive language identification in Dravidian code mixed social media text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunil</namePart>
<namePart type="family">Saumya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyoti</namePart>
<namePart type="given">Prakash</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First 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="family">Kumar M</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hate speech and offensive language recognition in social media platforms have been an active field of research over recent years. In non-native English spoken countries, social media texts are mostly in code mixed or script mixed/switched form. The current study presents extensive experiments using multiple machine learning, deep learning, and transfer learning models to detect offensive content on Twitter. The data set used for this study are in Tanglish (Tamil and English), Manglish (Malayalam and English) code-mixed, and Malayalam script-mixed. The experimental results showed that 1 to 6-gram character TF-IDF features are better for the said task. The best performing models were naive bayes, logistic regression, and vanilla neural network for the dataset Tamil code-mix, Malayalam code-mixed, and Malayalam script-mixed, respectively instead of more popular transfer learning models such as BERT and ULMFiT and hybrid deep models.</abstract>
<identifier type="citekey">saumya-etal-2021-offensive</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.5</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>36</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Offensive language identification in Dravidian code mixed social media text
%A Saumya, Sunil
%A Kumar, Abhinav
%A Singh, Jyoti Prakash
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Kumar M, Anand
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%S Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv
%F saumya-etal-2021-offensive
%X Hate speech and offensive language recognition in social media platforms have been an active field of research over recent years. In non-native English spoken countries, social media texts are mostly in code mixed or script mixed/switched form. The current study presents extensive experiments using multiple machine learning, deep learning, and transfer learning models to detect offensive content on Twitter. The data set used for this study are in Tanglish (Tamil and English), Manglish (Malayalam and English) code-mixed, and Malayalam script-mixed. The experimental results showed that 1 to 6-gram character TF-IDF features are better for the said task. The best performing models were naive bayes, logistic regression, and vanilla neural network for the dataset Tamil code-mix, Malayalam code-mixed, and Malayalam script-mixed, respectively instead of more popular transfer learning models such as BERT and ULMFiT and hybrid deep models.
%U https://aclanthology.org/2021.dravidianlangtech-1.5
%P 36-45
Markdown (Informal)
[Offensive language identification in Dravidian code mixed social media text](https://aclanthology.org/2021.dravidianlangtech-1.5) (Saumya et al., DravidianLangTech 2021)
ACL