@inproceedings{mandalam-sharma-2021-sentiment,
title = "Sentiment Analysis of {D}ravidian Code Mixed Data",
author = "Mandalam, Asrita Venkata and
Sharma, Yashvardhan",
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-1.6",
pages = "46--54",
abstract = "This paper presents the methodologies implemented while classifying Dravidian code-mixed comments according to their polarity. With datasets of code-mixed Tamil and Malayalam available, three methods are proposed - a sub-word level model, a word embedding based model and a machine learning based architecture. The sub-word and word embedding based models utilized Long Short Term Memory (LSTM) network along with language-specific preprocessing while the machine learning model used term frequency{--}inverse document frequency (TF-IDF) vectorization along with a Logistic Regression model. The sub-word level model was submitted to the the track {`}Sentiment Analysis for Dravidian Languages in Code-Mixed Text{'} proposed by Forum of Information Retrieval Evaluation in 2020 (FIRE 2020). Although it received a rank of 5 and 12 for the Tamil and Malayalam tasks respectively in the FIRE 2020 track, this paper improves upon the results by a margin to attain final weighted F1-scores of 0.65 for the Tamil task and 0.68 for the Malayalam task. The former score is equivalent to that attained by the highest ranked team of the Tamil track.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mandalam-sharma-2021-sentiment">
<titleInfo>
<title>Sentiment Analysis of Dravidian Code Mixed Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asrita</namePart>
<namePart type="given">Venkata</namePart>
<namePart type="family">Mandalam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yashvardhan</namePart>
<namePart type="family">Sharma</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>This paper presents the methodologies implemented while classifying Dravidian code-mixed comments according to their polarity. With datasets of code-mixed Tamil and Malayalam available, three methods are proposed - a sub-word level model, a word embedding based model and a machine learning based architecture. The sub-word and word embedding based models utilized Long Short Term Memory (LSTM) network along with language-specific preprocessing while the machine learning model used term frequency–inverse document frequency (TF-IDF) vectorization along with a Logistic Regression model. The sub-word level model was submitted to the the track ‘Sentiment Analysis for Dravidian Languages in Code-Mixed Text’ proposed by Forum of Information Retrieval Evaluation in 2020 (FIRE 2020). Although it received a rank of 5 and 12 for the Tamil and Malayalam tasks respectively in the FIRE 2020 track, this paper improves upon the results by a margin to attain final weighted F1-scores of 0.65 for the Tamil task and 0.68 for the Malayalam task. The former score is equivalent to that attained by the highest ranked team of the Tamil track.</abstract>
<identifier type="citekey">mandalam-sharma-2021-sentiment</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.6</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>46</start>
<end>54</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sentiment Analysis of Dravidian Code Mixed Data
%A Mandalam, Asrita Venkata
%A Sharma, Yashvardhan
%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 mandalam-sharma-2021-sentiment
%X This paper presents the methodologies implemented while classifying Dravidian code-mixed comments according to their polarity. With datasets of code-mixed Tamil and Malayalam available, three methods are proposed - a sub-word level model, a word embedding based model and a machine learning based architecture. The sub-word and word embedding based models utilized Long Short Term Memory (LSTM) network along with language-specific preprocessing while the machine learning model used term frequency–inverse document frequency (TF-IDF) vectorization along with a Logistic Regression model. The sub-word level model was submitted to the the track ‘Sentiment Analysis for Dravidian Languages in Code-Mixed Text’ proposed by Forum of Information Retrieval Evaluation in 2020 (FIRE 2020). Although it received a rank of 5 and 12 for the Tamil and Malayalam tasks respectively in the FIRE 2020 track, this paper improves upon the results by a margin to attain final weighted F1-scores of 0.65 for the Tamil task and 0.68 for the Malayalam task. The former score is equivalent to that attained by the highest ranked team of the Tamil track.
%U https://aclanthology.org/2021.dravidianlangtech-1.6
%P 46-54
Markdown (Informal)
[Sentiment Analysis of Dravidian Code Mixed Data](https://aclanthology.org/2021.dravidianlangtech-1.6) (Mandalam & Sharma, DravidianLangTech 2021)
ACL
- Asrita Venkata Mandalam and Yashvardhan Sharma. 2021. Sentiment Analysis of Dravidian Code Mixed Data. In Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages, pages 46–54, Kyiv. Association for Computational Linguistics.