@inproceedings{verhoeven-daelemans-2014-clips,
title = "{CL}i{PS} Stylometry Investigation ({CSI}) corpus: A {D}utch corpus for the detection of age, gender, personality, sentiment and deception in text",
author = "Verhoeven, Ben and
Daelemans, Walter",
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/1_Paper.pdf",
pages = "3081--3085",
abstract = "We present the CLiPS Stylometry Investigation (CSI) corpus, a new Dutch corpus containing reviews and essays written by university students. It is designed to serve multiple purposes: detection of age, gender, authorship, personality, sentiment, deception, topic and genre. Another major advantage is its planned yearly expansion with each year{'}s new students. The corpus currently contains about 305,000 tokens spread over 749 documents. The average review length is 128 tokens; the average essay length is 1126 tokens. The corpus will be made available on the CLiPS website (www.clips.uantwerpen.be/datasets) and can freely be used for academic research purposes. An initial deception detection experiment was performed on this data. Deception detection is the task of automatically classifying a text as being either truthful or deceptive, in our case by examining the writing style of the author. This task has never been investigated for Dutch before. We performed a supervised machine learning experiment using the SVM algorithm in a 10-fold cross-validation setup. The only features were the token unigrams present in the training data. Using this simple method, we reached a state-of-the-art F-score of 72.2{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="verhoeven-daelemans-2014-clips">
<titleInfo>
<title>CLiPS Stylometry Investigation (CSI) corpus: A Dutch corpus for the detection of age, gender, personality, sentiment and deception in text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Verhoeven</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walter</namePart>
<namePart type="family">Daelemans</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 the CLiPS Stylometry Investigation (CSI) corpus, a new Dutch corpus containing reviews and essays written by university students. It is designed to serve multiple purposes: detection of age, gender, authorship, personality, sentiment, deception, topic and genre. Another major advantage is its planned yearly expansion with each year’s new students. The corpus currently contains about 305,000 tokens spread over 749 documents. The average review length is 128 tokens; the average essay length is 1126 tokens. The corpus will be made available on the CLiPS website (www.clips.uantwerpen.be/datasets) and can freely be used for academic research purposes. An initial deception detection experiment was performed on this data. Deception detection is the task of automatically classifying a text as being either truthful or deceptive, in our case by examining the writing style of the author. This task has never been investigated for Dutch before. We performed a supervised machine learning experiment using the SVM algorithm in a 10-fold cross-validation setup. The only features were the token unigrams present in the training data. Using this simple method, we reached a state-of-the-art F-score of 72.2%.</abstract>
<identifier type="citekey">verhoeven-daelemans-2014-clips</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3081</start>
<end>3085</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLiPS Stylometry Investigation (CSI) corpus: A Dutch corpus for the detection of age, gender, personality, sentiment and deception in text
%A Verhoeven, Ben
%A Daelemans, Walter
%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 verhoeven-daelemans-2014-clips
%X We present the CLiPS Stylometry Investigation (CSI) corpus, a new Dutch corpus containing reviews and essays written by university students. It is designed to serve multiple purposes: detection of age, gender, authorship, personality, sentiment, deception, topic and genre. Another major advantage is its planned yearly expansion with each year’s new students. The corpus currently contains about 305,000 tokens spread over 749 documents. The average review length is 128 tokens; the average essay length is 1126 tokens. The corpus will be made available on the CLiPS website (www.clips.uantwerpen.be/datasets) and can freely be used for academic research purposes. An initial deception detection experiment was performed on this data. Deception detection is the task of automatically classifying a text as being either truthful or deceptive, in our case by examining the writing style of the author. This task has never been investigated for Dutch before. We performed a supervised machine learning experiment using the SVM algorithm in a 10-fold cross-validation setup. The only features were the token unigrams present in the training data. Using this simple method, we reached a state-of-the-art F-score of 72.2%.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1_Paper.pdf
%P 3081-3085
Markdown (Informal)
[CLiPS Stylometry Investigation (CSI) corpus: A Dutch corpus for the detection of age, gender, personality, sentiment and deception in text](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1_Paper.pdf) (Verhoeven & Daelemans, LREC 2014)
ACL