@inproceedings{scheffler-2014-german,
title = "A {G}erman {T}witter Snapshot",
author = "Scheffler, Tatjana",
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/1146_Paper.pdf",
pages = "2284--2289",
abstract = "We present a new corpus of German tweets. Due to the relatively small number of German messages on Twitter, it is possible to collect a virtually complete snapshot of German twitter messages over a period of time. In this paper, we present our collection method which produced a 24 million tweet corpus, representing a large majority of all German tweets sent in April, 2013. Further, we analyze this representative data set and characterize the German twitterverse. While German Twitter data is similar to other Twitter data in terms of its temporal distribution, German Twitter users are much more reluctant to share geolocation information with their tweets. Finally, the corpus collection method allows for a study of discourse phenomena in the Twitter data, structured into discussion threads.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scheffler-2014-german">
<titleInfo>
<title>A German Twitter Snapshot</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatjana</namePart>
<namePart type="family">Scheffler</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 new corpus of German tweets. Due to the relatively small number of German messages on Twitter, it is possible to collect a virtually complete snapshot of German twitter messages over a period of time. In this paper, we present our collection method which produced a 24 million tweet corpus, representing a large majority of all German tweets sent in April, 2013. Further, we analyze this representative data set and characterize the German twitterverse. While German Twitter data is similar to other Twitter data in terms of its temporal distribution, German Twitter users are much more reluctant to share geolocation information with their tweets. Finally, the corpus collection method allows for a study of discourse phenomena in the Twitter data, structured into discussion threads.</abstract>
<identifier type="citekey">scheffler-2014-german</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1146_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2284</start>
<end>2289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A German Twitter Snapshot
%A Scheffler, Tatjana
%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 scheffler-2014-german
%X We present a new corpus of German tweets. Due to the relatively small number of German messages on Twitter, it is possible to collect a virtually complete snapshot of German twitter messages over a period of time. In this paper, we present our collection method which produced a 24 million tweet corpus, representing a large majority of all German tweets sent in April, 2013. Further, we analyze this representative data set and characterize the German twitterverse. While German Twitter data is similar to other Twitter data in terms of its temporal distribution, German Twitter users are much more reluctant to share geolocation information with their tweets. Finally, the corpus collection method allows for a study of discourse phenomena in the Twitter data, structured into discussion threads.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1146_Paper.pdf
%P 2284-2289
Markdown (Informal)
[A German Twitter Snapshot](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1146_Paper.pdf) (Scheffler, LREC 2014)
ACL
- Tatjana Scheffler. 2014. A German Twitter Snapshot. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2284–2289, Reykjavik, Iceland. European Language Resources Association (ELRA).