@inproceedings{rygl-horak-2012-similarity,
title = "Similarity Ranking as Attribute for Machine Learning Approach to Authorship Identification",
author = "Rygl, Jan and
Hor{\'a}k, Ale{\v{s}}",
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/618_Paper.pdf",
pages = "726--729",
abstract = "In the authorship identification task, examples of short writings of N authors and an anonymous document written by one of these N authors are given. The task is to determine the authorship of the anonymous text. Practically all approaches solved this problem with machine learning methods. The input attributes for the machine learning process are usually formed by stylistic or grammatical properties of individual documents or a defined similarity between a document and an author. In this paper, we present the results of an experiment to extend the machine learning attributes by ranking the similarity between a document and an author: we transform the similarity between an unknown document and one of the N authors to the order in which the author is the most similar to the document in the set of N authors. The comparison of similarity probability and similarity ranking was made using the Support Vector Machines algorithm. The results show that machine learning methods perform slightly better with attributes based on the ranking of similarity than with previously used similarity between an author and a document.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rygl-horak-2012-similarity">
<titleInfo>
<title>Similarity Ranking as Attribute for Machine Learning Approach to Authorship Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Rygl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleš</namePart>
<namePart type="family">Horák</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 the authorship identification task, examples of short writings of N authors and an anonymous document written by one of these N authors are given. The task is to determine the authorship of the anonymous text. Practically all approaches solved this problem with machine learning methods. The input attributes for the machine learning process are usually formed by stylistic or grammatical properties of individual documents or a defined similarity between a document and an author. In this paper, we present the results of an experiment to extend the machine learning attributes by ranking the similarity between a document and an author: we transform the similarity between an unknown document and one of the N authors to the order in which the author is the most similar to the document in the set of N authors. The comparison of similarity probability and similarity ranking was made using the Support Vector Machines algorithm. The results show that machine learning methods perform slightly better with attributes based on the ranking of similarity than with previously used similarity between an author and a document.</abstract>
<identifier type="citekey">rygl-horak-2012-similarity</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/618_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>726</start>
<end>729</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Similarity Ranking as Attribute for Machine Learning Approach to Authorship Identification
%A Rygl, Jan
%A Horák, Aleš
%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 rygl-horak-2012-similarity
%X In the authorship identification task, examples of short writings of N authors and an anonymous document written by one of these N authors are given. The task is to determine the authorship of the anonymous text. Practically all approaches solved this problem with machine learning methods. The input attributes for the machine learning process are usually formed by stylistic or grammatical properties of individual documents or a defined similarity between a document and an author. In this paper, we present the results of an experiment to extend the machine learning attributes by ranking the similarity between a document and an author: we transform the similarity between an unknown document and one of the N authors to the order in which the author is the most similar to the document in the set of N authors. The comparison of similarity probability and similarity ranking was made using the Support Vector Machines algorithm. The results show that machine learning methods perform slightly better with attributes based on the ranking of similarity than with previously used similarity between an author and a document.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/618_Paper.pdf
%P 726-729
Markdown (Informal)
[Similarity Ranking as Attribute for Machine Learning Approach to Authorship Identification](http://www.lrec-conf.org/proceedings/lrec2012/pdf/618_Paper.pdf) (Rygl & Horák, LREC 2012)
ACL