@inproceedings{maks-vossen-2012-building,
title = "Building a fine-grained subjectivity lexicon from a web corpus",
author = "Maks, Isa and
Vossen, Piek",
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/1018_Paper.pdf",
pages = "3070--3076",
abstract = "In this paper we propose a method to build fine-grained subjectivity lexicons including nouns, verbs and adjectives. The method, which is applied for Dutch, is based on the comparison of word frequencies of three corpora: Wikipedia, News and News comments. Comparison of the corpora is carried out with two measures: log-likelihood ratio and a percentage difference calculation. The first step of the method involves subjectivity identification, i.e. determining if a word is subjective or not. The second step aims at the identification of more fine-grained subjectivity which is the distinction between actor subjectivity and speaker / writer subjectivity. The results suggest that this approach can be usefully applied producing subjectivity lexicons of high quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maks-vossen-2012-building">
<titleInfo>
<title>Building a fine-grained subjectivity lexicon from a web corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isa</namePart>
<namePart type="family">Maks</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Piek</namePart>
<namePart type="family">Vossen</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 this paper we propose a method to build fine-grained subjectivity lexicons including nouns, verbs and adjectives. The method, which is applied for Dutch, is based on the comparison of word frequencies of three corpora: Wikipedia, News and News comments. Comparison of the corpora is carried out with two measures: log-likelihood ratio and a percentage difference calculation. The first step of the method involves subjectivity identification, i.e. determining if a word is subjective or not. The second step aims at the identification of more fine-grained subjectivity which is the distinction between actor subjectivity and speaker / writer subjectivity. The results suggest that this approach can be usefully applied producing subjectivity lexicons of high quality.</abstract>
<identifier type="citekey">maks-vossen-2012-building</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1018_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3070</start>
<end>3076</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Building a fine-grained subjectivity lexicon from a web corpus
%A Maks, Isa
%A Vossen, Piek
%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 maks-vossen-2012-building
%X In this paper we propose a method to build fine-grained subjectivity lexicons including nouns, verbs and adjectives. The method, which is applied for Dutch, is based on the comparison of word frequencies of three corpora: Wikipedia, News and News comments. Comparison of the corpora is carried out with two measures: log-likelihood ratio and a percentage difference calculation. The first step of the method involves subjectivity identification, i.e. determining if a word is subjective or not. The second step aims at the identification of more fine-grained subjectivity which is the distinction between actor subjectivity and speaker / writer subjectivity. The results suggest that this approach can be usefully applied producing subjectivity lexicons of high quality.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1018_Paper.pdf
%P 3070-3076
Markdown (Informal)
[Building a fine-grained subjectivity lexicon from a web corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1018_Paper.pdf) (Maks & Vossen, LREC 2012)
ACL