@inproceedings{kulkarni-etal-2021-l3cubemahasent,
title = "{L}3{C}ube{M}aha{S}ent: A {M}arathi Tweet-based Sentiment Analysis Dataset",
author = "Kulkarni, Atharva and
Mandhane, Meet and
Likhitkar, Manali and
Kshirsagar, Gayatri and
Joshi, Raviraj",
editor = "De Clercq, Orphee and
Balahur, Alexandra and
Sedoc, Joao and
Barriere, Valentin and
Tafreshi, Shabnam and
Buechel, Sven and
Hoste, Veronique",
booktitle = "Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wassa-1.23",
pages = "213--220",
abstract = "Sentiment analysis is one of the most fundamental tasks in Natural Language Processing. Popular languages like English, Arabic, Russian, Mandarin, and also Indian languages such as Hindi, Bengali, Tamil have seen a significant amount of work in this area. However, the Marathi language which is the third most popular language in India still lags behind due to the absence of proper datasets. In this paper, we present the first major publicly available Marathi Sentiment Analysis Dataset - L3CubeMahaSent. It is curated using tweets extracted from various Maharashtrian personalities{'} Twitter accounts. Our dataset consists of {\textasciitilde}16,000 distinct tweets classified in three broad classes viz. positive, negative, and neutral. We also present the guidelines using which we annotated the tweets. Finally, we present the statistics of our dataset and baseline classification results using CNN, LSTM, ULMFiT, and BERT based models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kulkarni-etal-2021-l3cubemahasent">
<titleInfo>
<title>L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atharva</namePart>
<namePart type="family">Kulkarni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meet</namePart>
<namePart type="family">Mandhane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manali</namePart>
<namePart type="family">Likhitkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gayatri</namePart>
<namePart type="family">Kshirsagar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raviraj</namePart>
<namePart type="family">Joshi</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 Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Orphee</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joao</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sven</namePart>
<namePart type="family">Buechel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment analysis is one of the most fundamental tasks in Natural Language Processing. Popular languages like English, Arabic, Russian, Mandarin, and also Indian languages such as Hindi, Bengali, Tamil have seen a significant amount of work in this area. However, the Marathi language which is the third most popular language in India still lags behind due to the absence of proper datasets. In this paper, we present the first major publicly available Marathi Sentiment Analysis Dataset - L3CubeMahaSent. It is curated using tweets extracted from various Maharashtrian personalities’ Twitter accounts. Our dataset consists of ~16,000 distinct tweets classified in three broad classes viz. positive, negative, and neutral. We also present the guidelines using which we annotated the tweets. Finally, we present the statistics of our dataset and baseline classification results using CNN, LSTM, ULMFiT, and BERT based models.</abstract>
<identifier type="citekey">kulkarni-etal-2021-l3cubemahasent</identifier>
<location>
<url>https://aclanthology.org/2021.wassa-1.23</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>213</start>
<end>220</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset
%A Kulkarni, Atharva
%A Mandhane, Meet
%A Likhitkar, Manali
%A Kshirsagar, Gayatri
%A Joshi, Raviraj
%Y De Clercq, Orphee
%Y Balahur, Alexandra
%Y Sedoc, Joao
%Y Barriere, Valentin
%Y Tafreshi, Shabnam
%Y Buechel, Sven
%Y Hoste, Veronique
%S Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F kulkarni-etal-2021-l3cubemahasent
%X Sentiment analysis is one of the most fundamental tasks in Natural Language Processing. Popular languages like English, Arabic, Russian, Mandarin, and also Indian languages such as Hindi, Bengali, Tamil have seen a significant amount of work in this area. However, the Marathi language which is the third most popular language in India still lags behind due to the absence of proper datasets. In this paper, we present the first major publicly available Marathi Sentiment Analysis Dataset - L3CubeMahaSent. It is curated using tweets extracted from various Maharashtrian personalities’ Twitter accounts. Our dataset consists of ~16,000 distinct tweets classified in three broad classes viz. positive, negative, and neutral. We also present the guidelines using which we annotated the tweets. Finally, we present the statistics of our dataset and baseline classification results using CNN, LSTM, ULMFiT, and BERT based models.
%U https://aclanthology.org/2021.wassa-1.23
%P 213-220
Markdown (Informal)
[L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset](https://aclanthology.org/2021.wassa-1.23) (Kulkarni et al., WASSA 2021)
ACL
- Atharva Kulkarni, Meet Mandhane, Manali Likhitkar, Gayatri Kshirsagar, and Raviraj Joshi. 2021. L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset. In Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 213–220, Online. Association for Computational Linguistics.