@inproceedings{spracklin-etal-2008-using,
title = "Using the Complexity of the Distribution of Lexical Elements as a Feature in Authorship Attribution",
author = "Spracklin, Leanne and
Inkpen, Diana and
Nayak, Amiya",
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/892_paper.pdf",
abstract = "Traditional Authorship Attribution models extract normalized counts of lexical elements such as nouns, common words and punctuation and use these normalized counts or ratios as features for author fingerprinting. The text is viewed as a bag-of-words and the order of words and their position relative to other words is largely ignored. We propose a new method of feature extraction which quantifies the distribution of lexical elements within the text using Kolmogorov complexity estimates. Testing carried out on blog corpora indicates that such measures outperform ratios when used as features in an SVM authorship attribution model. Moreover, by adding complexity estimates to a model using ratios, we were able to increase the F-measure by 5.2-11.8{\%}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="spracklin-etal-2008-using">
<titleInfo>
<title>Using the Complexity of the Distribution of Lexical Elements as a Feature in Authorship Attribution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leanne</namePart>
<namePart type="family">Spracklin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="family">Inkpen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amiya</namePart>
<namePart type="family">Nayak</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>Traditional Authorship Attribution models extract normalized counts of lexical elements such as nouns, common words and punctuation and use these normalized counts or ratios as features for author fingerprinting. The text is viewed as a bag-of-words and the order of words and their position relative to other words is largely ignored. We propose a new method of feature extraction which quantifies the distribution of lexical elements within the text using Kolmogorov complexity estimates. Testing carried out on blog corpora indicates that such measures outperform ratios when used as features in an SVM authorship attribution model. Moreover, by adding complexity estimates to a model using ratios, we were able to increase the F-measure by 5.2-11.8%</abstract>
<identifier type="citekey">spracklin-etal-2008-using</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/892_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using the Complexity of the Distribution of Lexical Elements as a Feature in Authorship Attribution
%A Spracklin, Leanne
%A Inkpen, Diana
%A Nayak, Amiya
%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 spracklin-etal-2008-using
%X Traditional Authorship Attribution models extract normalized counts of lexical elements such as nouns, common words and punctuation and use these normalized counts or ratios as features for author fingerprinting. The text is viewed as a bag-of-words and the order of words and their position relative to other words is largely ignored. We propose a new method of feature extraction which quantifies the distribution of lexical elements within the text using Kolmogorov complexity estimates. Testing carried out on blog corpora indicates that such measures outperform ratios when used as features in an SVM authorship attribution model. Moreover, by adding complexity estimates to a model using ratios, we were able to increase the F-measure by 5.2-11.8%
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/892_paper.pdf
Markdown (Informal)
[Using the Complexity of the Distribution of Lexical Elements as a Feature in Authorship Attribution](http://www.lrec-conf.org/proceedings/lrec2008/pdf/892_paper.pdf) (Spracklin et al., LREC 2008)
ACL