@inproceedings{ciobotaru-etal-2022-red,
title = "{RED} v2: Enhancing {RED} Dataset for Multi-Label Emotion Detection",
author = "Ciobotaru, Alexandra and
Constantinescu, Mihai Vlad and
Dinu, Liviu P. and
Dumitrescu, Stefan",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.149",
pages = "1392--1399",
abstract = "RED (Romanian Emotion Dataset) is a machine learning-based resource developed for the automatic detection of emotions in Romanian texts, containing single-label annotated tweets with one of the following emotions: joy, fear, sadness, anger and neutral. In this work, we propose REDv2, an open-source extension of RED by adding two more emotions, trust and surprise, and by widening the annotation schema so that the resulted novel dataset is multi-label. We show the overall reliability of our dataset by computing inter-annotator agreements per tweet using a formula suitable for our annotation setup and we aggregate all annotators{'} opinions into two variants of ground truth, one suitable for multi-label classification and the other suitable for text regression. We propose strong baselines with two transformer models, the Romanian BERT and the multilingual XLM-Roberta model, in both categorical and regression settings.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ciobotaru-etal-2022-red">
<titleInfo>
<title>RED v2: Enhancing RED Dataset for Multi-Label Emotion Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Ciobotaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="given">Vlad</namePart>
<namePart type="family">Constantinescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liviu</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Dinu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Dumitrescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>RED (Romanian Emotion Dataset) is a machine learning-based resource developed for the automatic detection of emotions in Romanian texts, containing single-label annotated tweets with one of the following emotions: joy, fear, sadness, anger and neutral. In this work, we propose REDv2, an open-source extension of RED by adding two more emotions, trust and surprise, and by widening the annotation schema so that the resulted novel dataset is multi-label. We show the overall reliability of our dataset by computing inter-annotator agreements per tweet using a formula suitable for our annotation setup and we aggregate all annotators’ opinions into two variants of ground truth, one suitable for multi-label classification and the other suitable for text regression. We propose strong baselines with two transformer models, the Romanian BERT and the multilingual XLM-Roberta model, in both categorical and regression settings.</abstract>
<identifier type="citekey">ciobotaru-etal-2022-red</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.149</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1392</start>
<end>1399</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RED v2: Enhancing RED Dataset for Multi-Label Emotion Detection
%A Ciobotaru, Alexandra
%A Constantinescu, Mihai Vlad
%A Dinu, Liviu P.
%A Dumitrescu, Stefan
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F ciobotaru-etal-2022-red
%X RED (Romanian Emotion Dataset) is a machine learning-based resource developed for the automatic detection of emotions in Romanian texts, containing single-label annotated tweets with one of the following emotions: joy, fear, sadness, anger and neutral. In this work, we propose REDv2, an open-source extension of RED by adding two more emotions, trust and surprise, and by widening the annotation schema so that the resulted novel dataset is multi-label. We show the overall reliability of our dataset by computing inter-annotator agreements per tweet using a formula suitable for our annotation setup and we aggregate all annotators’ opinions into two variants of ground truth, one suitable for multi-label classification and the other suitable for text regression. We propose strong baselines with two transformer models, the Romanian BERT and the multilingual XLM-Roberta model, in both categorical and regression settings.
%U https://aclanthology.org/2022.lrec-1.149
%P 1392-1399
Markdown (Informal)
[RED v2: Enhancing RED Dataset for Multi-Label Emotion Detection](https://aclanthology.org/2022.lrec-1.149) (Ciobotaru et al., LREC 2022)
ACL