@inproceedings{xu-etal-2020-semi,
title = "Semi-Automatic Construction and Refinement of an Annotated Corpus for a Deep Learning Framework for Emotion Classification",
author = "Xu, Jiajun and
Masuda, Kyosuke and
Nishizaki, Hiromitsu and
Fukumoto, Fumiyo and
Suzuki, Yoshimi",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.200",
pages = "1611--1617",
abstract = "In the case of using a deep learning (machine learning) framework for emotion classification, one significant difficulty faced is the requirement of building a large, emotion corpus in which each sentence is assigned emotion labels. As a result, there is a high cost in terms of time and money associated with the construction of such a corpus. Therefore, this paper proposes a method of creating a semi-automatically constructed emotion corpus. For the purpose of this study sentences were mined from Twitter using some emotional seed words that were selected from a dictionary in which the emotion words were well-defined. Tweets were retrieved by one emotional seed word, and the retrieved sentences were assigned emotion labels based on the emotion category of the seed word. It was evident from the findings that the deep learning-based emotion classification model could not achieve high levels of accuracy in emotion classification because the semi-automatically constructed corpus had many errors when assigning emotion labels. In this paper, therefore, an approach for improving the quality of the emotion labels by automatically correcting the errors of emotion labels is proposed and tested. The experimental results showed that the proposed method worked well, and the classification accuracy rate was improved to 55.1{\%} from 44.9{\%} on the Twitter emotion classification task.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2020-semi">
<titleInfo>
<title>Semi-Automatic Construction and Refinement of an Annotated Corpus for a Deep Learning Framework for Emotion Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyosuke</namePart>
<namePart type="family">Masuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiromitsu</namePart>
<namePart type="family">Nishizaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fumiyo</namePart>
<namePart type="family">Fukumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshimi</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In the case of using a deep learning (machine learning) framework for emotion classification, one significant difficulty faced is the requirement of building a large, emotion corpus in which each sentence is assigned emotion labels. As a result, there is a high cost in terms of time and money associated with the construction of such a corpus. Therefore, this paper proposes a method of creating a semi-automatically constructed emotion corpus. For the purpose of this study sentences were mined from Twitter using some emotional seed words that were selected from a dictionary in which the emotion words were well-defined. Tweets were retrieved by one emotional seed word, and the retrieved sentences were assigned emotion labels based on the emotion category of the seed word. It was evident from the findings that the deep learning-based emotion classification model could not achieve high levels of accuracy in emotion classification because the semi-automatically constructed corpus had many errors when assigning emotion labels. In this paper, therefore, an approach for improving the quality of the emotion labels by automatically correcting the errors of emotion labels is proposed and tested. The experimental results showed that the proposed method worked well, and the classification accuracy rate was improved to 55.1% from 44.9% on the Twitter emotion classification task.</abstract>
<identifier type="citekey">xu-etal-2020-semi</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.200</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1611</start>
<end>1617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semi-Automatic Construction and Refinement of an Annotated Corpus for a Deep Learning Framework for Emotion Classification
%A Xu, Jiajun
%A Masuda, Kyosuke
%A Nishizaki, Hiromitsu
%A Fukumoto, Fumiyo
%A Suzuki, Yoshimi
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F xu-etal-2020-semi
%X In the case of using a deep learning (machine learning) framework for emotion classification, one significant difficulty faced is the requirement of building a large, emotion corpus in which each sentence is assigned emotion labels. As a result, there is a high cost in terms of time and money associated with the construction of such a corpus. Therefore, this paper proposes a method of creating a semi-automatically constructed emotion corpus. For the purpose of this study sentences were mined from Twitter using some emotional seed words that were selected from a dictionary in which the emotion words were well-defined. Tweets were retrieved by one emotional seed word, and the retrieved sentences were assigned emotion labels based on the emotion category of the seed word. It was evident from the findings that the deep learning-based emotion classification model could not achieve high levels of accuracy in emotion classification because the semi-automatically constructed corpus had many errors when assigning emotion labels. In this paper, therefore, an approach for improving the quality of the emotion labels by automatically correcting the errors of emotion labels is proposed and tested. The experimental results showed that the proposed method worked well, and the classification accuracy rate was improved to 55.1% from 44.9% on the Twitter emotion classification task.
%U https://aclanthology.org/2020.lrec-1.200
%P 1611-1617
Markdown (Informal)
[Semi-Automatic Construction and Refinement of an Annotated Corpus for a Deep Learning Framework for Emotion Classification](https://aclanthology.org/2020.lrec-1.200) (Xu et al., LREC 2020)
ACL