@inproceedings{elahimanesh-etal-2012-improving,
title = "Improving K-Nearest Neighbor Efficacy for {F}arsi Text Classification",
author = "Elahimanesh, Mohammad Hossein and
Minaei, Behrouz and
Malekinezhad, Hossein",
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/903_Paper.pdf",
pages = "1618--1621",
abstract = "One of the common processes in the field of text mining is text classification. Because of the complex nature of Farsi language, words with separate parts and combined verbs, the most of text classification systems are not applicable to Farsi texts. K-Nearest Neighbors (KNN) is one of the most popular used methods for text classification and presents good performance in experiments on different datasets. A method to improve the classification performance of KNN is proposed in this paper. Effects of removing or maintaining stop words, applying N-Grams with different lengths are also studied. For this study, a portion of a standard Farsi corpus called Hamshahri1 and articles of some archived newspapers are used. As the results indicate, classification efficiency improves by applying this approach especially when eight-grams indexing method and removing stop words are applied. Using N-grams with lengths more than 3 characters, presented very encouraging results for Farsi text classification. The Results of classification using our method are compared with the results obtained by mentioned related works.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="elahimanesh-etal-2012-improving">
<titleInfo>
<title>Improving K-Nearest Neighbor Efficacy for Farsi Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Hossein</namePart>
<namePart type="family">Elahimanesh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Behrouz</namePart>
<namePart type="family">Minaei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hossein</namePart>
<namePart type="family">Malekinezhad</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>One of the common processes in the field of text mining is text classification. Because of the complex nature of Farsi language, words with separate parts and combined verbs, the most of text classification systems are not applicable to Farsi texts. K-Nearest Neighbors (KNN) is one of the most popular used methods for text classification and presents good performance in experiments on different datasets. A method to improve the classification performance of KNN is proposed in this paper. Effects of removing or maintaining stop words, applying N-Grams with different lengths are also studied. For this study, a portion of a standard Farsi corpus called Hamshahri1 and articles of some archived newspapers are used. As the results indicate, classification efficiency improves by applying this approach especially when eight-grams indexing method and removing stop words are applied. Using N-grams with lengths more than 3 characters, presented very encouraging results for Farsi text classification. The Results of classification using our method are compared with the results obtained by mentioned related works.</abstract>
<identifier type="citekey">elahimanesh-etal-2012-improving</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/903_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1618</start>
<end>1621</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving K-Nearest Neighbor Efficacy for Farsi Text Classification
%A Elahimanesh, Mohammad Hossein
%A Minaei, Behrouz
%A Malekinezhad, Hossein
%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 elahimanesh-etal-2012-improving
%X One of the common processes in the field of text mining is text classification. Because of the complex nature of Farsi language, words with separate parts and combined verbs, the most of text classification systems are not applicable to Farsi texts. K-Nearest Neighbors (KNN) is one of the most popular used methods for text classification and presents good performance in experiments on different datasets. A method to improve the classification performance of KNN is proposed in this paper. Effects of removing or maintaining stop words, applying N-Grams with different lengths are also studied. For this study, a portion of a standard Farsi corpus called Hamshahri1 and articles of some archived newspapers are used. As the results indicate, classification efficiency improves by applying this approach especially when eight-grams indexing method and removing stop words are applied. Using N-grams with lengths more than 3 characters, presented very encouraging results for Farsi text classification. The Results of classification using our method are compared with the results obtained by mentioned related works.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/903_Paper.pdf
%P 1618-1621
Markdown (Informal)
[Improving K-Nearest Neighbor Efficacy for Farsi Text Classification](http://www.lrec-conf.org/proceedings/lrec2012/pdf/903_Paper.pdf) (Elahimanesh et al., LREC 2012)
ACL