Publikation: LEIA : Linguistic Embeddings for the Identification of Affect
Dateien
Datum
Autor:innen
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
European Union (EU): 101020961
European Union (EU): 101020961
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
The wealth of text data generated by social media has enabled new kinds of analysis of emotions with language models. These models are often trained on small and costly datasets of text annotations produced by readers who guess the emotions expressed by others in social media posts. This affects the quality of emotion identification methods due to training data size limitations and noise in the production of labels used in model development. We present LEIA, a model for emotion identification in text that has been trained on a dataset of more than 6 million posts with self-annotated emotion labels for happiness, affection, sadness, anger, and fear. LEIA is based on a word masking method that enhances the learning of emotion words during model pre-training. LEIA achieves macro-F1 values of approximately 73 on three in-domain test datasets, outperforming other supervised and unsupervised methods in a strong benchmark that shows that LEIA generalizes across posts, users, and time periods. We further perform an out-of-domain evaluation on five different datasets of social media and other sources, showing LEIA’s robust performance across media, data collection methods, and annotation schemes. Our results show that LEIA generalizes its classification of anger, happiness, and sadness beyond the domain it was trained on. LEIA can be applied in future research to provide better identification of emotions in text from the perspective of the writer.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
AROYEHUN, Segun Toafeek, Lukas MALIK, Hannah METZLER, Nikolas HAIMERL, Anna DI NATALE, David GARCIA, 2023. LEIA : Linguistic Embeddings for the Identification of Affect. In: EPJ Data Science. Springer. 2023, 12, 52. eISSN 2193-1127. Available under: doi: 10.1140/epjds/s13688-023-00427-0BibTex
@article{Aroyehun2023Lingu-68948, year={2023}, doi={10.1140/epjds/s13688-023-00427-0}, title={LEIA : Linguistic Embeddings for the Identification of Affect}, volume={12}, journal={EPJ Data Science}, author={Aroyehun, Segun Toafeek and Malik, Lukas and Metzler, Hannah and Haimerl, Nikolas and Di Natale, Anna and Garcia, David}, note={Article Number: 52} }
RDF
<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/68948"> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/42"/> <dc:contributor>Di Natale, Anna</dc:contributor> <dc:creator>Aroyehun, Segun Toafeek</dc:creator> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dcterms:abstract>The wealth of text data generated by social media has enabled new kinds of analysis of emotions with language models. These models are often trained on small and costly datasets of text annotations produced by readers who guess the emotions expressed by others in social media posts. This affects the quality of emotion identification methods due to training data size limitations and noise in the production of labels used in model development. We present LEIA, a model for emotion identification in text that has been trained on a dataset of more than 6 million posts with self-annotated emotion labels for happiness, affection, sadness, anger, and fear. LEIA is based on a word masking method that enhances the learning of emotion words during model pre-training. LEIA achieves macro-F1 values of approximately 73 on three in-domain test datasets, outperforming other supervised and unsupervised methods in a strong benchmark that shows that LEIA generalizes across posts, users, and time periods. We further perform an out-of-domain evaluation on five different datasets of social media and other sources, showing LEIA’s robust performance across media, data collection methods, and annotation schemes. Our results show that LEIA generalizes its classification of anger, happiness, and sadness beyond the domain it was trained on. LEIA can be applied in future research to provide better identification of emotions in text from the perspective of the writer.</dcterms:abstract> <dc:contributor>Aroyehun, Segun Toafeek</dc:contributor> <dc:creator>Haimerl, Nikolas</dc:creator> <dc:creator>Garcia, David</dc:creator> <dc:contributor>Metzler, Hannah</dc:contributor> <dc:language>eng</dc:language> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/68948/1/Aroyehun_2-q2g8w6w3lt031.pdf"/> <dcterms:title>LEIA : Linguistic Embeddings for the Identification of Affect</dcterms:title> <dc:rights>Attribution 4.0 International</dc:rights> <dc:creator>Di Natale, Anna</dc:creator> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/4.0/"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-01-05T10:25:42Z</dc:date> <dc:contributor>Garcia, David</dc:contributor> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/42"/> <dc:contributor>Malik, Lukas</dc:contributor> <dc:creator>Malik, Lukas</dc:creator> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/68948"/> <dcterms:issued>2023</dcterms:issued> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/68948/1/Aroyehun_2-q2g8w6w3lt031.pdf"/> <dc:creator>Metzler, Hannah</dc:creator> <dc:contributor>Haimerl, Nikolas</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2024-01-05T10:25:42Z</dcterms:available> </rdf:Description> </rdf:RDF>