@inproceedings{treurniet-etal-2012-collection,
title = "Collection of a corpus of {D}utch {SMS}",
author = "Treurniet, Maaske and
De Clercq, Orph{\'e}e and
van den Heuvel, Henk and
Oostdijk, Nelleke",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/537_Paper.pdf",
pages = "2268--2273",
abstract = "In this paper we present the first freely available corpus of Dutch text messages containing data originating from the Netherlands and Flanders. This corpus has been collected in the framework of the SoNaR project and constitutes a viable part of this 500-million-word corpus. About 53,000 text messages were collected on a large scale, based on voluntary donations. These messages will be distributed as such. In this paper we focus on the data collection processes involved and after studying the effect of media coverage we show that especially free publicity in newspapers and on social media networks results in more contributions. All SMS are provided with metadata information. Looking at the composition of the corpus, it becomes visible that a small number of people have contributed a large amount of data, in total 272 people have contributed to the corpus during three months. The number of women contributing to the corpus is larger than the number of men, but male contributors submitted larger amounts of data. This corpus will be of paramount importance for sociolinguistic research and normalisation studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="treurniet-etal-2012-collection">
<titleInfo>
<title>Collection of a corpus of Dutch SMS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maaske</namePart>
<namePart type="family">Treurniet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelleke</namePart>
<namePart type="family">Oostdijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present the first freely available corpus of Dutch text messages containing data originating from the Netherlands and Flanders. This corpus has been collected in the framework of the SoNaR project and constitutes a viable part of this 500-million-word corpus. About 53,000 text messages were collected on a large scale, based on voluntary donations. These messages will be distributed as such. In this paper we focus on the data collection processes involved and after studying the effect of media coverage we show that especially free publicity in newspapers and on social media networks results in more contributions. All SMS are provided with metadata information. Looking at the composition of the corpus, it becomes visible that a small number of people have contributed a large amount of data, in total 272 people have contributed to the corpus during three months. The number of women contributing to the corpus is larger than the number of men, but male contributors submitted larger amounts of data. This corpus will be of paramount importance for sociolinguistic research and normalisation studies.</abstract>
<identifier type="citekey">treurniet-etal-2012-collection</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/537_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2268</start>
<end>2273</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Collection of a corpus of Dutch SMS
%A Treurniet, Maaske
%A De Clercq, Orphée
%A van den Heuvel, Henk
%A Oostdijk, Nelleke
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F treurniet-etal-2012-collection
%X In this paper we present the first freely available corpus of Dutch text messages containing data originating from the Netherlands and Flanders. This corpus has been collected in the framework of the SoNaR project and constitutes a viable part of this 500-million-word corpus. About 53,000 text messages were collected on a large scale, based on voluntary donations. These messages will be distributed as such. In this paper we focus on the data collection processes involved and after studying the effect of media coverage we show that especially free publicity in newspapers and on social media networks results in more contributions. All SMS are provided with metadata information. Looking at the composition of the corpus, it becomes visible that a small number of people have contributed a large amount of data, in total 272 people have contributed to the corpus during three months. The number of women contributing to the corpus is larger than the number of men, but male contributors submitted larger amounts of data. This corpus will be of paramount importance for sociolinguistic research and normalisation studies.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/537_Paper.pdf
%P 2268-2273
Markdown (Informal)
[Collection of a corpus of Dutch SMS](http://www.lrec-conf.org/proceedings/lrec2012/pdf/537_Paper.pdf) (Treurniet et al., LREC 2012)
ACL
- Maaske Treurniet, Orphée De Clercq, Henk van den Heuvel, and Nelleke Oostdijk. 2012. Collection of a corpus of Dutch SMS. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2268–2273, Istanbul, Turkey. European Language Resources Association (ELRA).