@inproceedings{gombar-etal-2017-debunking,
title = "Debunking Sentiment Lexicons: A Case of Domain-Specific Sentiment Classification for {C}roatian",
author = "Gombar, Paula and
Medi{\'c}, Zoran and
Alagi{\'c}, Domagoj and
{\v{S}}najder, Jan",
editor = "Erjavec, Toma{\v{z}} and
Piskorski, Jakub and
Pivovarova, Lidia and
{\v{S}}najder, Jan and
Steinberger, Josef and
Yangarber, Roman",
booktitle = "Proceedings of the 6th Workshop on {B}alto-{S}lavic Natural Language Processing",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-1409",
doi = "10.18653/v1/W17-1409",
pages = "54--59",
abstract = "Sentiment lexicons are widely used as an intuitive and inexpensive way of tackling sentiment classification, often within a simple lexicon word-counting approach or as part of a supervised model. However, it is an open question whether these approaches can compete with supervised models that use only word-representation features. We address this question in the context of domain-specific sentiment classification for Croatian. We experiment with the graph-based acquisition of sentiment lexicons, analyze their quality, and investigate how effectively they can be used in sentiment classification. Our results indicate that, even with as few as 500 labeled instances, a supervised model substantially outperforms a word-counting model. We also observe that adding lexicon-based features does not significantly improve supervised sentiment classification.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gombar-etal-2017-debunking">
<titleInfo>
<title>Debunking Sentiment Lexicons: A Case of Domain-Specific Sentiment Classification for Croatian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Gombar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoran</namePart>
<namePart type="family">Medić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Domagoj</namePart>
<namePart type="family">Alagić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomaž</namePart>
<namePart type="family">Erjavec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Piskorski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="family">Pivovarova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Steinberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sentiment lexicons are widely used as an intuitive and inexpensive way of tackling sentiment classification, often within a simple lexicon word-counting approach or as part of a supervised model. However, it is an open question whether these approaches can compete with supervised models that use only word-representation features. We address this question in the context of domain-specific sentiment classification for Croatian. We experiment with the graph-based acquisition of sentiment lexicons, analyze their quality, and investigate how effectively they can be used in sentiment classification. Our results indicate that, even with as few as 500 labeled instances, a supervised model substantially outperforms a word-counting model. We also observe that adding lexicon-based features does not significantly improve supervised sentiment classification.</abstract>
<identifier type="citekey">gombar-etal-2017-debunking</identifier>
<identifier type="doi">10.18653/v1/W17-1409</identifier>
<location>
<url>https://aclanthology.org/W17-1409</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>54</start>
<end>59</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Debunking Sentiment Lexicons: A Case of Domain-Specific Sentiment Classification for Croatian
%A Gombar, Paula
%A Medić, Zoran
%A Alagić, Domagoj
%A Šnajder, Jan
%Y Erjavec, Tomaž
%Y Piskorski, Jakub
%Y Pivovarova, Lidia
%Y Šnajder, Jan
%Y Steinberger, Josef
%Y Yangarber, Roman
%S Proceedings of the 6th Workshop on Balto-Slavic Natural Language Processing
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F gombar-etal-2017-debunking
%X Sentiment lexicons are widely used as an intuitive and inexpensive way of tackling sentiment classification, often within a simple lexicon word-counting approach or as part of a supervised model. However, it is an open question whether these approaches can compete with supervised models that use only word-representation features. We address this question in the context of domain-specific sentiment classification for Croatian. We experiment with the graph-based acquisition of sentiment lexicons, analyze their quality, and investigate how effectively they can be used in sentiment classification. Our results indicate that, even with as few as 500 labeled instances, a supervised model substantially outperforms a word-counting model. We also observe that adding lexicon-based features does not significantly improve supervised sentiment classification.
%R 10.18653/v1/W17-1409
%U https://aclanthology.org/W17-1409
%U https://doi.org/10.18653/v1/W17-1409
%P 54-59
Markdown (Informal)
[Debunking Sentiment Lexicons: A Case of Domain-Specific Sentiment Classification for Croatian](https://aclanthology.org/W17-1409) (Gombar et al., BSNLP 2017)
ACL