@inproceedings{tang-etal-2014-clustering,
title = "Clustering tweets using{W}ikipedia concepts",
author = "Tang, Guoyu and
Xia, Yunqing and
Wang, Weizhi and
Lau, Raymond and
Zheng, Fang",
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/83_Paper.pdf",
pages = "2262--2267",
abstract = "Two challenging issues are notable in tweet clustering. Firstly, the sparse data problem is serious since no tweet can be longer than 140 characters. Secondly, synonymy and polysemy are rather common because users intend to present a unique meaning with a great number of manners in tweets. Enlightened by the recent research which indicates Wikipedia is promising in representing text, we exploit Wikipedia concepts in representing tweets with concept vectors. We address the polysemy issue with a Bayesian model, and the synonymy issue by exploiting the Wikipedia redirections. To further alleviate the sparse data problem, we further make use of three types of out-links in Wikipedia. Evaluation on a twitter dataset shows that the concept model outperforms the traditional VSM model in tweet clustering.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2014-clustering">
<titleInfo>
<title>Clustering tweets usingWikipedia concepts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guoyu</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunqing</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weizhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="family">Lau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Zheng</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>Two challenging issues are notable in tweet clustering. Firstly, the sparse data problem is serious since no tweet can be longer than 140 characters. Secondly, synonymy and polysemy are rather common because users intend to present a unique meaning with a great number of manners in tweets. Enlightened by the recent research which indicates Wikipedia is promising in representing text, we exploit Wikipedia concepts in representing tweets with concept vectors. We address the polysemy issue with a Bayesian model, and the synonymy issue by exploiting the Wikipedia redirections. To further alleviate the sparse data problem, we further make use of three types of out-links in Wikipedia. Evaluation on a twitter dataset shows that the concept model outperforms the traditional VSM model in tweet clustering.</abstract>
<identifier type="citekey">tang-etal-2014-clustering</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/83_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2262</start>
<end>2267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Clustering tweets usingWikipedia concepts
%A Tang, Guoyu
%A Xia, Yunqing
%A Wang, Weizhi
%A Lau, Raymond
%A Zheng, Fang
%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 tang-etal-2014-clustering
%X Two challenging issues are notable in tweet clustering. Firstly, the sparse data problem is serious since no tweet can be longer than 140 characters. Secondly, synonymy and polysemy are rather common because users intend to present a unique meaning with a great number of manners in tweets. Enlightened by the recent research which indicates Wikipedia is promising in representing text, we exploit Wikipedia concepts in representing tweets with concept vectors. We address the polysemy issue with a Bayesian model, and the synonymy issue by exploiting the Wikipedia redirections. To further alleviate the sparse data problem, we further make use of three types of out-links in Wikipedia. Evaluation on a twitter dataset shows that the concept model outperforms the traditional VSM model in tweet clustering.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/83_Paper.pdf
%P 2262-2267
Markdown (Informal)
[Clustering tweets usingWikipedia concepts](http://www.lrec-conf.org/proceedings/lrec2014/pdf/83_Paper.pdf) (Tang et al., LREC 2014)
ACL
- Guoyu Tang, Yunqing Xia, Weizhi Wang, Raymond Lau, and Fang Zheng. 2014. Clustering tweets usingWikipedia concepts. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2262–2267, Reykjavik, Iceland. European Language Resources Association (ELRA).