Login
Document type:
Konferenzbeitrag / Conference Paper
Title:
CODE at CheckThat! 2022: Multi-class fake news detection of news articles with BERT
Collection editors:
Faggioli, Guglielmo; Ferro, Nicola; Hanbury, Allan; Potthast, Martin
Title of conference publication:
Proceedings of the Working Notes of CLEF 2022 - Conference and Labs of the Evaluation Forum
Subtitle of conference publication:
Bologna, Italy, September 5th to 8th, 2022
Series title:
CEUR Workshop Proceedings
Series volume:
3180
Conference title:
Conference and Labs of the Evaluation Forum (13., 2022, Bologna)
Venue:
Bologna, Italy
Year of conference:
2022
Date of conference beginning:
05.09.2022
Date of conference ending:
08.09.2022
URL conference paper:
Year:
2022
Pages from - to:
444-455
Language:
Englisch
Keywords:
Sequence Classification ; Deep Learning ; Transformers ; BERT
Abstract:
The following system description presents our approach for detecting fake news in texts. The given task was formulated as a multi-class classification problem. Our approach is based on the combination of two BERT-based classification models: One model determines whether the textual content is relevant to the task; the second model assigns it a truth value. Starting from a pre-trained model for language representation, we fine-tuned these models on the given classification task in supervised tra... »
ISBN:
1613-0073
Department:
Fakultät für Informatik
Institute:
INF 7 - Institut für Datensicherheit
Chair:
Geierhos, Michaela
Research Hub UniBw M:
CODE
Open Access yes or no?:
Ja / Yes
Type of OA license:
CC BY 4.0
Licence URL:
BibTeX