@inproceedings{prochnow-etal-2024-idem-idioms,
title = "{IDEM}: The {ID}ioms with {EM}otions Dataset for Emotion Recognition",
author = {Prochnow, Alexander and
Bendler, Johannes E. and
Lange, Caroline and
Tzavellos, Foivos Ioannis and
G{\"o}ritzer, Bas Marco and
ten Thij, Marijn and
Batista-Navarro, Riza},
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.752",
pages = "8569--8579",
abstract = "Idiomatic expressions are used in everyday language and typically convey affect, i.e., emotion. However, very little work investigating the extent to which automated methods can recognise emotions expressed in idiom-containing text has been undertaken. This can be attributed to the lack of emotion-labelled datasets that support the development and evaluation of such methods. In this paper, we present the IDioms with EMotions (IDEM) dataset consisting of a total of 9685 idiom-containing sentences that were generated and labelled with any one of 36 emotion types, with the help of the GPT-4 generative language model. Human validation by two independent annotators showed that more than 51{\%} of the generated sentences are ideal examples, with the annotators reaching an agreement rate of 62{\%} measured in terms of Cohen{'}s Kappa coefficient. To establish baseline performance on IDEM, various transformer-based emotion recognition approaches were implemented and evaluated. Results show that a RoBERTa model fine-tuned as a sequence classifier obtains a weighted F1-score of 58.73{\%}, when the sequence provided as input specifies the idiom contained in a given sentence, together with its definition. Since this input configuration is based on the assumption that the idiom contained in the given sentence is already known, we also sought to assess the feasibility of automatically identifying the idioms contained in IDEM sentences. To this end, a hybrid idiom identification approach combining a rule-based method and a deep learning-based model was developed, whose performance on IDEM was determined to be 84.99{\%} in terms of F1-score.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prochnow-etal-2024-idem-idioms">
<titleInfo>
<title>IDEM: The IDioms with EMotions Dataset for Emotion Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Prochnow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Bendler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Lange</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Foivos</namePart>
<namePart type="given">Ioannis</namePart>
<namePart type="family">Tzavellos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bas</namePart>
<namePart type="given">Marco</namePart>
<namePart type="family">Göritzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marijn</namePart>
<namePart type="family">ten Thij</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riza</namePart>
<namePart type="family">Batista-Navarro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Idiomatic expressions are used in everyday language and typically convey affect, i.e., emotion. However, very little work investigating the extent to which automated methods can recognise emotions expressed in idiom-containing text has been undertaken. This can be attributed to the lack of emotion-labelled datasets that support the development and evaluation of such methods. In this paper, we present the IDioms with EMotions (IDEM) dataset consisting of a total of 9685 idiom-containing sentences that were generated and labelled with any one of 36 emotion types, with the help of the GPT-4 generative language model. Human validation by two independent annotators showed that more than 51% of the generated sentences are ideal examples, with the annotators reaching an agreement rate of 62% measured in terms of Cohen’s Kappa coefficient. To establish baseline performance on IDEM, various transformer-based emotion recognition approaches were implemented and evaluated. Results show that a RoBERTa model fine-tuned as a sequence classifier obtains a weighted F1-score of 58.73%, when the sequence provided as input specifies the idiom contained in a given sentence, together with its definition. Since this input configuration is based on the assumption that the idiom contained in the given sentence is already known, we also sought to assess the feasibility of automatically identifying the idioms contained in IDEM sentences. To this end, a hybrid idiom identification approach combining a rule-based method and a deep learning-based model was developed, whose performance on IDEM was determined to be 84.99% in terms of F1-score.</abstract>
<identifier type="citekey">prochnow-etal-2024-idem-idioms</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.752</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8569</start>
<end>8579</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IDEM: The IDioms with EMotions Dataset for Emotion Recognition
%A Prochnow, Alexander
%A Bendler, Johannes E.
%A Lange, Caroline
%A Tzavellos, Foivos Ioannis
%A Göritzer, Bas Marco
%A ten Thij, Marijn
%A Batista-Navarro, Riza
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F prochnow-etal-2024-idem-idioms
%X Idiomatic expressions are used in everyday language and typically convey affect, i.e., emotion. However, very little work investigating the extent to which automated methods can recognise emotions expressed in idiom-containing text has been undertaken. This can be attributed to the lack of emotion-labelled datasets that support the development and evaluation of such methods. In this paper, we present the IDioms with EMotions (IDEM) dataset consisting of a total of 9685 idiom-containing sentences that were generated and labelled with any one of 36 emotion types, with the help of the GPT-4 generative language model. Human validation by two independent annotators showed that more than 51% of the generated sentences are ideal examples, with the annotators reaching an agreement rate of 62% measured in terms of Cohen’s Kappa coefficient. To establish baseline performance on IDEM, various transformer-based emotion recognition approaches were implemented and evaluated. Results show that a RoBERTa model fine-tuned as a sequence classifier obtains a weighted F1-score of 58.73%, when the sequence provided as input specifies the idiom contained in a given sentence, together with its definition. Since this input configuration is based on the assumption that the idiom contained in the given sentence is already known, we also sought to assess the feasibility of automatically identifying the idioms contained in IDEM sentences. To this end, a hybrid idiom identification approach combining a rule-based method and a deep learning-based model was developed, whose performance on IDEM was determined to be 84.99% in terms of F1-score.
%U https://aclanthology.org/2024.lrec-main.752
%P 8569-8579
Markdown (Informal)
[IDEM: The IDioms with EMotions Dataset for Emotion Recognition](https://aclanthology.org/2024.lrec-main.752) (Prochnow et al., LREC-COLING 2024)
ACL
- Alexander Prochnow, Johannes E. Bendler, Caroline Lange, Foivos Ioannis Tzavellos, Bas Marco Göritzer, Marijn ten Thij, and Riza Batista-Navarro. 2024. IDEM: The IDioms with EMotions Dataset for Emotion Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 8569–8579, Torino, Italia. ELRA and ICCL.