@inproceedings{allison-guthrie-2008-authorship,
title = "Authorship Attribution of {E}-Mail: Comparing Classifiers over a New Corpus for Evaluation",
author = "Allison, Ben and
Guthrie, Louise",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/552_paper.pdf",
abstract = "The release of the Enron corpus provided a unique resource for studying aspects of email use, because it is largely unfiltered, and therefore presents a relatively complete collection of emails for a reasonably large number of correspondents. This paper describes a newly created subcorpus of the Enron emails which we suggest can be used to test techniqes for authorship attribution, and further shows the application of three different classification methods to this task to present baseline results. Two of the classifiers used are are standard, and have been shown to perform well in the literature, and one of the classifiers is novel and based on concurrent work that proposes a Bayesian hierarchical distribution for word counts in documents. For each of the classifiers, we present results using six text representations, including use of linguistic structures derived from a parser as well as lexical information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="allison-guthrie-2008-authorship">
<titleInfo>
<title>Authorship Attribution of E-Mail: Comparing Classifiers over a New Corpus for Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Allison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louise</namePart>
<namePart type="family">Guthrie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The release of the Enron corpus provided a unique resource for studying aspects of email use, because it is largely unfiltered, and therefore presents a relatively complete collection of emails for a reasonably large number of correspondents. This paper describes a newly created subcorpus of the Enron emails which we suggest can be used to test techniqes for authorship attribution, and further shows the application of three different classification methods to this task to present baseline results. Two of the classifiers used are are standard, and have been shown to perform well in the literature, and one of the classifiers is novel and based on concurrent work that proposes a Bayesian hierarchical distribution for word counts in documents. For each of the classifiers, we present results using six text representations, including use of linguistic structures derived from a parser as well as lexical information.</abstract>
<identifier type="citekey">allison-guthrie-2008-authorship</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/552_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Authorship Attribution of E-Mail: Comparing Classifiers over a New Corpus for Evaluation
%A Allison, Ben
%A Guthrie, Louise
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F allison-guthrie-2008-authorship
%X The release of the Enron corpus provided a unique resource for studying aspects of email use, because it is largely unfiltered, and therefore presents a relatively complete collection of emails for a reasonably large number of correspondents. This paper describes a newly created subcorpus of the Enron emails which we suggest can be used to test techniqes for authorship attribution, and further shows the application of three different classification methods to this task to present baseline results. Two of the classifiers used are are standard, and have been shown to perform well in the literature, and one of the classifiers is novel and based on concurrent work that proposes a Bayesian hierarchical distribution for word counts in documents. For each of the classifiers, we present results using six text representations, including use of linguistic structures derived from a parser as well as lexical information.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/552_paper.pdf
Markdown (Informal)
[Authorship Attribution of E-Mail: Comparing Classifiers over a New Corpus for Evaluation](http://www.lrec-conf.org/proceedings/lrec2008/pdf/552_paper.pdf) (Allison & Guthrie, LREC 2008)
ACL