@inproceedings{skeppstedt-etal-2016-active,
title = "Active learning for detection of stance components",
author = "Skeppstedt, Maria and
Sahlgren, Magnus and
Paradis, Carita and
Kerren, Andreas",
editor = "Nissim, Malvina and
Patti, Viviana and
Plank, Barbara",
booktitle = "Proceedings of the Workshop on Computational Modeling of People{'}s Opinions, Personality, and Emotions in Social Media ({PEOPLES})",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-4306",
pages = "50--59",
abstract = "Automatic detection of five language components, which are all relevant for expressing opinions and for stance taking, was studied: positive sentiment, negative sentiment, speculation, contrast and condition. A resource-aware approach was taken, which included manual annotation of 500 training samples and the use of limited lexical resources. Active learning was compared to random selection of training data, as well as to a lexicon-based method. Active learning was successful for the categories speculation, contrast and condition, but not for the two sentiment categories, for which results achieved when using active learning were similar to those achieved when applying a random selection of training data. This difference is likely due to a larger variation in how sentiment is expressed than in how speakers express the other three categories. This larger variation was also shown by the lower recall results achieved by the lexicon-based approach for sentiment than for the categories speculation, contrast and condition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="skeppstedt-etal-2016-active">
<titleInfo>
<title>Active learning for detection of stance components</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Skeppstedt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magnus</namePart>
<namePart type="family">Sahlgren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carita</namePart>
<namePart type="family">Paradis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Kerren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media (PEOPLES)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malvina</namePart>
<namePart type="family">Nissim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic detection of five language components, which are all relevant for expressing opinions and for stance taking, was studied: positive sentiment, negative sentiment, speculation, contrast and condition. A resource-aware approach was taken, which included manual annotation of 500 training samples and the use of limited lexical resources. Active learning was compared to random selection of training data, as well as to a lexicon-based method. Active learning was successful for the categories speculation, contrast and condition, but not for the two sentiment categories, for which results achieved when using active learning were similar to those achieved when applying a random selection of training data. This difference is likely due to a larger variation in how sentiment is expressed than in how speakers express the other three categories. This larger variation was also shown by the lower recall results achieved by the lexicon-based approach for sentiment than for the categories speculation, contrast and condition.</abstract>
<identifier type="citekey">skeppstedt-etal-2016-active</identifier>
<location>
<url>https://aclanthology.org/W16-4306</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>50</start>
<end>59</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Active learning for detection of stance components
%A Skeppstedt, Maria
%A Sahlgren, Magnus
%A Paradis, Carita
%A Kerren, Andreas
%Y Nissim, Malvina
%Y Patti, Viviana
%Y Plank, Barbara
%S Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media (PEOPLES)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F skeppstedt-etal-2016-active
%X Automatic detection of five language components, which are all relevant for expressing opinions and for stance taking, was studied: positive sentiment, negative sentiment, speculation, contrast and condition. A resource-aware approach was taken, which included manual annotation of 500 training samples and the use of limited lexical resources. Active learning was compared to random selection of training data, as well as to a lexicon-based method. Active learning was successful for the categories speculation, contrast and condition, but not for the two sentiment categories, for which results achieved when using active learning were similar to those achieved when applying a random selection of training data. This difference is likely due to a larger variation in how sentiment is expressed than in how speakers express the other three categories. This larger variation was also shown by the lower recall results achieved by the lexicon-based approach for sentiment than for the categories speculation, contrast and condition.
%U https://aclanthology.org/W16-4306
%P 50-59
Markdown (Informal)
[Active learning for detection of stance components](https://aclanthology.org/W16-4306) (Skeppstedt et al., PEOPLES 2016)
ACL
- Maria Skeppstedt, Magnus Sahlgren, Carita Paradis, and Andreas Kerren. 2016. Active learning for detection of stance components. In Proceedings of the Workshop on Computational Modeling of People’s Opinions, Personality, and Emotions in Social Media (PEOPLES), pages 50–59, Osaka, Japan. The COLING 2016 Organizing Committee.