@inproceedings{uryupina-etal-2014-sentube,
title = "{S}en{T}ube: A Corpus for Sentiment Analysis on {Y}ou{T}ube Social Media",
author = "Uryupina, Olga and
Plank, Barbara and
Severyn, Aliaksei and
Rotondi, Agata and
Moschitti, Alessandro",
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/180_Paper.pdf",
pages = "4244--4249",
abstract = "In this paper we present SenTube {--} a dataset of user-generated comments on YouTube videos annotated for information content and sentiment polarity. It contains annotations that allow to develop classifiers for several important NLP tasks: (i) sentiment analysis, (ii) text categorization (relatedness of a comment to video and/or product), (iii) spam detection, and (iv) prediction of comment informativeness. The SenTube corpus favors the development of research on indexing and searching YouTube videos exploiting information derived from comments. The corpus will cover several languages: at the moment, we focus on English and Italian, with Spanish and Dutch parts scheduled for the later stages of the project. For all the languages, we collect videos for the same set of products, thus offering possibilities for multi- and cross-lingual experiments. The paper provides annotation guidelines, corpus statistics and annotator agreement details.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="uryupina-etal-2014-sentube">
<titleInfo>
<title>SenTube: A Corpus for Sentiment Analysis on YouTube Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Uryupina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aliaksei</namePart>
<namePart type="family">Severyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agata</namePart>
<namePart type="family">Rotondi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Moschitti</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>In this paper we present SenTube – a dataset of user-generated comments on YouTube videos annotated for information content and sentiment polarity. It contains annotations that allow to develop classifiers for several important NLP tasks: (i) sentiment analysis, (ii) text categorization (relatedness of a comment to video and/or product), (iii) spam detection, and (iv) prediction of comment informativeness. The SenTube corpus favors the development of research on indexing and searching YouTube videos exploiting information derived from comments. The corpus will cover several languages: at the moment, we focus on English and Italian, with Spanish and Dutch parts scheduled for the later stages of the project. For all the languages, we collect videos for the same set of products, thus offering possibilities for multi- and cross-lingual experiments. The paper provides annotation guidelines, corpus statistics and annotator agreement details.</abstract>
<identifier type="citekey">uryupina-etal-2014-sentube</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/180_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>4244</start>
<end>4249</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SenTube: A Corpus for Sentiment Analysis on YouTube Social Media
%A Uryupina, Olga
%A Plank, Barbara
%A Severyn, Aliaksei
%A Rotondi, Agata
%A Moschitti, Alessandro
%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 uryupina-etal-2014-sentube
%X In this paper we present SenTube – a dataset of user-generated comments on YouTube videos annotated for information content and sentiment polarity. It contains annotations that allow to develop classifiers for several important NLP tasks: (i) sentiment analysis, (ii) text categorization (relatedness of a comment to video and/or product), (iii) spam detection, and (iv) prediction of comment informativeness. The SenTube corpus favors the development of research on indexing and searching YouTube videos exploiting information derived from comments. The corpus will cover several languages: at the moment, we focus on English and Italian, with Spanish and Dutch parts scheduled for the later stages of the project. For all the languages, we collect videos for the same set of products, thus offering possibilities for multi- and cross-lingual experiments. The paper provides annotation guidelines, corpus statistics and annotator agreement details.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/180_Paper.pdf
%P 4244-4249
Markdown (Informal)
[SenTube: A Corpus for Sentiment Analysis on YouTube Social Media](http://www.lrec-conf.org/proceedings/lrec2014/pdf/180_Paper.pdf) (Uryupina et al., LREC 2014)
ACL
- Olga Uryupina, Barbara Plank, Aliaksei Severyn, Agata Rotondi, and Alessandro Moschitti. 2014. SenTube: A Corpus for Sentiment Analysis on YouTube Social Media. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4244–4249, Reykjavik, Iceland. European Language Resources Association (ELRA).