Comparing ChatGPT to Human Raters and Sentiment Analysis Tools for German Children’s Literature

Publikationstyp:
Konferenzbeitrag
Metadaten:
Abstract
In this paper, we apply the ChatGPT Large Language Model (gpt-3.5-turbo) to the 4books dataset, a German language collection of children’s and young adult novels comprising a total of 22.860 sentences annotated for valence by 80 human raters. We verify if ChatGPT can (a) compare to the behaviour of human raters and/or (b) outperform state of the art sentiment analysis tools. Results show that, while inter-rater agreement with human readers is low (independently from the inclusion/exclusion of context), effciency scores are comparable to the most advanced sentiment analysis tools.
Autoren
Editoren
  • Artjoms Šeļa
  • Fotis Jannidis
  • Iza Romanowska
Conference finish date
2023
ISSN
1613-0073
Zeitschrift
Proceedings of the Computational Humanities Research Conference 2023
Conference place
Paris, France
Name of conference
CHR 2023: Computational Humanities Research Conference
Online publication date
2023
Paginierung
333 - 343, 11
Datum der Veröffentlichung
2023
Herausgeber
CEUR
Herausgeber URL
https://ceur-ws.org/Vol-3558/paper3340.pdf
Datum der Datenerfassung
2023
Conference start date
2023
Titel
Comparing ChatGPT to Human Raters and Sentiment Analysis Tools for German Children’s Literature
Ausgabe der Zeitschrift
3558

Datenquelle: Manual

Andere Metadatenquellen:
Beziehungen:
Eigentum von

Werkzeuge