@inproceedings{li-etal-2016-emotion,
title = "Emotion Corpus Construction Based on Selection from Hashtags",
author = "Li, Minglei and
Long, Yunfei and
Qin, Lu and
Li, Wenjie",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1291",
pages = "1845--1849",
abstract = "The availability of labelled corpus is of great importance for supervised learning in emotion classification tasks. Because it is time-consuming to manually label text, hashtags have been used as naturally annotated labels to obtain a large amount of labelled training data from microblog. However, natural hashtags contain too much noise for it to be used directly in learning algorithms. In this paper, we design a three-stage semi-automatic method to construct an emotion corpus from microblogs. Firstly, a lexicon based voting approach is used to verify the hashtag automatically. Secondly, a SVM based classifier is used to select the data whose natural labels are consistent with the predicted labels. Finally, the remaining data will be manually examined to filter out the noisy data. Out of about 48K filtered Chinese microblogs, 39k microblogs are selected to form the final corpus with the Kappa value reaching over 0.92 for the automatic parts and over 0.81 for the manual part. The proportion of automatic selection reaches 54.1{\%}. Thus, the method can reduce about 44.5{\%} of manual workload for acquiring quality data. Experiment on a classifier trained on this corpus shows that it achieves comparable results compared to the manually annotated NLP{\&}CC2013 corpus.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2016-emotion">
<titleInfo>
<title>Emotion Corpus Construction Based on Selection from Hashtags</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minglei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunfei</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The availability of labelled corpus is of great importance for supervised learning in emotion classification tasks. Because it is time-consuming to manually label text, hashtags have been used as naturally annotated labels to obtain a large amount of labelled training data from microblog. However, natural hashtags contain too much noise for it to be used directly in learning algorithms. In this paper, we design a three-stage semi-automatic method to construct an emotion corpus from microblogs. Firstly, a lexicon based voting approach is used to verify the hashtag automatically. Secondly, a SVM based classifier is used to select the data whose natural labels are consistent with the predicted labels. Finally, the remaining data will be manually examined to filter out the noisy data. Out of about 48K filtered Chinese microblogs, 39k microblogs are selected to form the final corpus with the Kappa value reaching over 0.92 for the automatic parts and over 0.81 for the manual part. The proportion of automatic selection reaches 54.1%. Thus, the method can reduce about 44.5% of manual workload for acquiring quality data. Experiment on a classifier trained on this corpus shows that it achieves comparable results compared to the manually annotated NLP&CC2013 corpus.</abstract>
<identifier type="citekey">li-etal-2016-emotion</identifier>
<location>
<url>https://aclanthology.org/L16-1291</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1845</start>
<end>1849</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Emotion Corpus Construction Based on Selection from Hashtags
%A Li, Minglei
%A Long, Yunfei
%A Qin, Lu
%A Li, Wenjie
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F li-etal-2016-emotion
%X The availability of labelled corpus is of great importance for supervised learning in emotion classification tasks. Because it is time-consuming to manually label text, hashtags have been used as naturally annotated labels to obtain a large amount of labelled training data from microblog. However, natural hashtags contain too much noise for it to be used directly in learning algorithms. In this paper, we design a three-stage semi-automatic method to construct an emotion corpus from microblogs. Firstly, a lexicon based voting approach is used to verify the hashtag automatically. Secondly, a SVM based classifier is used to select the data whose natural labels are consistent with the predicted labels. Finally, the remaining data will be manually examined to filter out the noisy data. Out of about 48K filtered Chinese microblogs, 39k microblogs are selected to form the final corpus with the Kappa value reaching over 0.92 for the automatic parts and over 0.81 for the manual part. The proportion of automatic selection reaches 54.1%. Thus, the method can reduce about 44.5% of manual workload for acquiring quality data. Experiment on a classifier trained on this corpus shows that it achieves comparable results compared to the manually annotated NLP&CC2013 corpus.
%U https://aclanthology.org/L16-1291
%P 1845-1849
Markdown (Informal)
[Emotion Corpus Construction Based on Selection from Hashtags](https://aclanthology.org/L16-1291) (Li et al., LREC 2016)
ACL
- Minglei Li, Yunfei Long, Lu Qin, and Wenjie Li. 2016. Emotion Corpus Construction Based on Selection from Hashtags. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 1845–1849, Portorož, Slovenia. European Language Resources Association (ELRA).