@inproceedings{tarkka-etal-2024-automated,
title = "Automated Emotion Annotation of {F}innish Parliamentary Speeches Using {GPT}-4",
author = "Tarkka, Otto and
Koljonen, Jaakko and
Korhonen, Markus and
Laine, Juuso and
Martiskainen, Kristian and
Elo, Kimmo and
Laippala, Veronika",
editor = "Fiser, Darja and
Eskevich, Maria and
Bordon, David",
booktitle = "Proceedings of the IV Workshop on Creating, Analysing, and Increasing Accessibility of Parliamentary Corpora (ParlaCLARIN) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.parlaclarin-1.11",
pages = "70--76",
abstract = "In this paper, we test the efficacy of using GPT-4 to annotate a dataset that is the used to train a BERT classifier for emotion analysis. Manual data annotation is often a laborious and expensive task and emotion annotation, specifically, has proved difficult even for expert annotators. We show that using GPT-4 can produce equally good results as doing data annotation manually while saving a lot of time and money. We train a BERT classifier on our automatically annotated dataset and get results that outperform a BERT classifier that is trained on machine translated data. Our paper shows how Large Language Models can be used to work with and analyse parliamentary corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tarkka-etal-2024-automated">
<titleInfo>
<title>Automated Emotion Annotation of Finnish Parliamentary Speeches Using GPT-4</title>
</titleInfo>
<name type="personal">
<namePart type="given">Otto</namePart>
<namePart type="family">Tarkka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaakko</namePart>
<namePart type="family">Koljonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juuso</namePart>
<namePart type="family">Laine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kristian</namePart>
<namePart type="family">Martiskainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kimmo</namePart>
<namePart type="family">Elo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Laippala</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 IV Workshop on Creating, Analysing, and Increasing Accessibility of Parliamentary Corpora (ParlaCLARIN) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Eskevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Bordon</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>In this paper, we test the efficacy of using GPT-4 to annotate a dataset that is the used to train a BERT classifier for emotion analysis. Manual data annotation is often a laborious and expensive task and emotion annotation, specifically, has proved difficult even for expert annotators. We show that using GPT-4 can produce equally good results as doing data annotation manually while saving a lot of time and money. We train a BERT classifier on our automatically annotated dataset and get results that outperform a BERT classifier that is trained on machine translated data. Our paper shows how Large Language Models can be used to work with and analyse parliamentary corpora.</abstract>
<identifier type="citekey">tarkka-etal-2024-automated</identifier>
<location>
<url>https://aclanthology.org/2024.parlaclarin-1.11</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>70</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automated Emotion Annotation of Finnish Parliamentary Speeches Using GPT-4
%A Tarkka, Otto
%A Koljonen, Jaakko
%A Korhonen, Markus
%A Laine, Juuso
%A Martiskainen, Kristian
%A Elo, Kimmo
%A Laippala, Veronika
%Y Fiser, Darja
%Y Eskevich, Maria
%Y Bordon, David
%S Proceedings of the IV Workshop on Creating, Analysing, and Increasing Accessibility of Parliamentary Corpora (ParlaCLARIN) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F tarkka-etal-2024-automated
%X In this paper, we test the efficacy of using GPT-4 to annotate a dataset that is the used to train a BERT classifier for emotion analysis. Manual data annotation is often a laborious and expensive task and emotion annotation, specifically, has proved difficult even for expert annotators. We show that using GPT-4 can produce equally good results as doing data annotation manually while saving a lot of time and money. We train a BERT classifier on our automatically annotated dataset and get results that outperform a BERT classifier that is trained on machine translated data. Our paper shows how Large Language Models can be used to work with and analyse parliamentary corpora.
%U https://aclanthology.org/2024.parlaclarin-1.11
%P 70-76
Markdown (Informal)
[Automated Emotion Annotation of Finnish Parliamentary Speeches Using GPT-4](https://aclanthology.org/2024.parlaclarin-1.11) (Tarkka et al., ParlaCLARIN-WS 2024)
ACL
- Otto Tarkka, Jaakko Koljonen, Markus Korhonen, Juuso Laine, Kristian Martiskainen, Kimmo Elo, and Veronika Laippala. 2024. Automated Emotion Annotation of Finnish Parliamentary Speeches Using GPT-4. In Proceedings of the IV Workshop on Creating, Analysing, and Increasing Accessibility of Parliamentary Corpora (ParlaCLARIN) @ LREC-COLING 2024, pages 70–76, Torino, Italia. ELRA and ICCL.