@inproceedings{refaee-rieser-2014-arabic,
title = "An {A}rabic {T}witter Corpus for Subjectivity and Sentiment Analysis",
author = "Refaee, Eshrag and
Rieser, Verena",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/317_Paper.pdf",
pages = "2268--2273",
abstract = "We present a newly collected data set of 8,868 gold-standard annotated Arabic feeds. The corpus is manually labelled for subjectivity and sentiment analysis (SSA) ( = 0:816). In addition, the corpus is annotated with a variety of motivated feature-sets that have previously shown positive impact on performance. The paper highlights issues posed by twitter as a genre, such as mixture of language varieties and topic-shifts. Our next step is to extend the current corpus, using online semi-supervised learning. A first sub-corpus will be released via the ELRA repository as part of this submission.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="refaee-rieser-2014-arabic">
<titleInfo>
<title>An Arabic Twitter Corpus for Subjectivity and Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eshrag</namePart>
<namePart type="family">Refaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Verena</namePart>
<namePart type="family">Rieser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a newly collected data set of 8,868 gold-standard annotated Arabic feeds. The corpus is manually labelled for subjectivity and sentiment analysis (SSA) ( = 0:816). In addition, the corpus is annotated with a variety of motivated feature-sets that have previously shown positive impact on performance. The paper highlights issues posed by twitter as a genre, such as mixture of language varieties and topic-shifts. Our next step is to extend the current corpus, using online semi-supervised learning. A first sub-corpus will be released via the ELRA repository as part of this submission.</abstract>
<identifier type="citekey">refaee-rieser-2014-arabic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/317_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2268</start>
<end>2273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Arabic Twitter Corpus for Subjectivity and Sentiment Analysis
%A Refaee, Eshrag
%A Rieser, Verena
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F refaee-rieser-2014-arabic
%X We present a newly collected data set of 8,868 gold-standard annotated Arabic feeds. The corpus is manually labelled for subjectivity and sentiment analysis (SSA) ( = 0:816). In addition, the corpus is annotated with a variety of motivated feature-sets that have previously shown positive impact on performance. The paper highlights issues posed by twitter as a genre, such as mixture of language varieties and topic-shifts. Our next step is to extend the current corpus, using online semi-supervised learning. A first sub-corpus will be released via the ELRA repository as part of this submission.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/317_Paper.pdf
%P 2268-2273
Markdown (Informal)
[An Arabic Twitter Corpus for Subjectivity and Sentiment Analysis](http://www.lrec-conf.org/proceedings/lrec2014/pdf/317_Paper.pdf) (Refaee & Rieser, LREC 2014)
ACL