@inproceedings{-etal-2020-multi,
title = "Multi-domain Tweet Corpora for Sentiment Analysis: Resource Creation and Evaluation",
author = "{Mamta} and
Ekbal, Asif and
Bhattacharyya, Pushpak and
Srivastava, Shikha and
Kumar, Alka and
Saha, Tista",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.621",
pages = "5046--5054",
abstract = "Due to the phenomenal growth of online content in recent time, sentiment analysis has attracted attention of the researchers and developers. A number of benchmark annotated corpora are available for domains like movie reviews, product reviews, hotel reviews, etc. The pervasiveness of social media has also lead to a huge amount of content posted by users who are misusing the power of social media to spread false beliefs and to negatively influence others. This type of content is coming from the domains like terrorism, cybersecurity, technology, social issues, etc. Mining of opinions from these domains is important to create a socially intelligent system to provide security to the public and to maintain the law and order situations. To the best of our knowledge, there is no publicly available tweet corpora for such pervasive domains. Hence, we firstly create a multi-domain tweet sentiment corpora and then establish a deep neural network based baseline framework to address the above mentioned issues. Annotated corpus has Cohen{'}s Kappa measurement for annotation quality of 0.770, which shows that the data is of acceptable quality. We are able to achieve 84.65{\%} accuracy for sentiment analysis by using an ensemble of Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit(GRU).",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="-etal-2020-multi">
<titleInfo>
<title>Multi-domain Tweet Corpora for Sentiment Analysis: Resource Creation and Evaluation</title>
</titleInfo>
<name>
<namePart>Mamta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asif</namePart>
<namePart type="family">Ekbal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikha</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alka</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tista</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Due to the phenomenal growth of online content in recent time, sentiment analysis has attracted attention of the researchers and developers. A number of benchmark annotated corpora are available for domains like movie reviews, product reviews, hotel reviews, etc. The pervasiveness of social media has also lead to a huge amount of content posted by users who are misusing the power of social media to spread false beliefs and to negatively influence others. This type of content is coming from the domains like terrorism, cybersecurity, technology, social issues, etc. Mining of opinions from these domains is important to create a socially intelligent system to provide security to the public and to maintain the law and order situations. To the best of our knowledge, there is no publicly available tweet corpora for such pervasive domains. Hence, we firstly create a multi-domain tweet sentiment corpora and then establish a deep neural network based baseline framework to address the above mentioned issues. Annotated corpus has Cohen’s Kappa measurement for annotation quality of 0.770, which shows that the data is of acceptable quality. We are able to achieve 84.65% accuracy for sentiment analysis by using an ensemble of Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit(GRU).</abstract>
<identifier type="citekey">-etal-2020-multi</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.621</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5046</start>
<end>5054</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-domain Tweet Corpora for Sentiment Analysis: Resource Creation and Evaluation
%A Ekbal, Asif
%A Bhattacharyya, Pushpak
%A Srivastava, Shikha
%A Kumar, Alka
%A Saha, Tista
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%A Mamta
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F -etal-2020-multi
%X Due to the phenomenal growth of online content in recent time, sentiment analysis has attracted attention of the researchers and developers. A number of benchmark annotated corpora are available for domains like movie reviews, product reviews, hotel reviews, etc. The pervasiveness of social media has also lead to a huge amount of content posted by users who are misusing the power of social media to spread false beliefs and to negatively influence others. This type of content is coming from the domains like terrorism, cybersecurity, technology, social issues, etc. Mining of opinions from these domains is important to create a socially intelligent system to provide security to the public and to maintain the law and order situations. To the best of our knowledge, there is no publicly available tweet corpora for such pervasive domains. Hence, we firstly create a multi-domain tweet sentiment corpora and then establish a deep neural network based baseline framework to address the above mentioned issues. Annotated corpus has Cohen’s Kappa measurement for annotation quality of 0.770, which shows that the data is of acceptable quality. We are able to achieve 84.65% accuracy for sentiment analysis by using an ensemble of Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and Gated Recurrent Unit(GRU).
%U https://aclanthology.org/2020.lrec-1.621
%P 5046-5054
Markdown (Informal)
[Multi-domain Tweet Corpora for Sentiment Analysis: Resource Creation and Evaluation](https://aclanthology.org/2020.lrec-1.621) (Mamta et al., LREC 2020)
ACL