@inproceedings{ljubesic-etal-2014-tweetcat,
title = "{T}weet{C}a{T}: a tool for building {T}witter corpora of smaller languages",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Fi{\v{s}}er, Darja and
Erjavec, Toma{\v{z}}",
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/834_Paper.pdf",
pages = "2279--2283",
abstract = "This paper presents TweetCaT, an open-source Python tool for building Twitter corpora that was designed for smaller languages. Using the Twitter search API and a set of seed terms, the tool identifies users tweeting in the language of interest together with their friends and followers. By running the tool for 235 days we tested it on the task of collecting two monitor corpora, one for Croatian and Serbian and the other for Slovene, thus also creating new and valuable resources for these languages. A post-processing step on the collected corpus is also described, which filters out users that tweet predominantly in a foreign language thus further cleans the collected corpora. Finally, an experiment on discriminating between Croatian and Serbian Twitter users is reported.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-etal-2014-tweetcat">
<titleInfo>
<title>TweetCaT: a tool for building Twitter corpora of smaller languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</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>This paper presents TweetCaT, an open-source Python tool for building Twitter corpora that was designed for smaller languages. Using the Twitter search API and a set of seed terms, the tool identifies users tweeting in the language of interest together with their friends and followers. By running the tool for 235 days we tested it on the task of collecting two monitor corpora, one for Croatian and Serbian and the other for Slovene, thus also creating new and valuable resources for these languages. A post-processing step on the collected corpus is also described, which filters out users that tweet predominantly in a foreign language thus further cleans the collected corpora. Finally, an experiment on discriminating between Croatian and Serbian Twitter users is reported.</abstract>
<identifier type="citekey">ljubesic-etal-2014-tweetcat</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/834_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2279</start>
<end>2283</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TweetCaT: a tool for building Twitter corpora of smaller languages
%A Ljubešić, Nikola
%A Fišer, Darja
%A Erjavec, Tomaž
%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 ljubesic-etal-2014-tweetcat
%X This paper presents TweetCaT, an open-source Python tool for building Twitter corpora that was designed for smaller languages. Using the Twitter search API and a set of seed terms, the tool identifies users tweeting in the language of interest together with their friends and followers. By running the tool for 235 days we tested it on the task of collecting two monitor corpora, one for Croatian and Serbian and the other for Slovene, thus also creating new and valuable resources for these languages. A post-processing step on the collected corpus is also described, which filters out users that tweet predominantly in a foreign language thus further cleans the collected corpora. Finally, an experiment on discriminating between Croatian and Serbian Twitter users is reported.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/834_Paper.pdf
%P 2279-2283
Markdown (Informal)
[TweetCaT: a tool for building Twitter corpora of smaller languages](http://www.lrec-conf.org/proceedings/lrec2014/pdf/834_Paper.pdf) (Ljubešić et al., LREC 2014)
ACL