Althabiti, S orcid.org/0000-0002-4646-0577, Alsalka, MA and Atwell, E orcid.org/0000-0001-9395-3764 (2022) SCUoL at CheckThat! 2022: Fake News Detection Using Transformer-Based Models. In: CEUR Workshop Proceedings. CLEF 2022 - Conference and Labs of the Evaluation Forum, 05-08 Sep 2022, Bologna, Italy. CEUR Workshop Proceedings , pp. 428-433.
Abstract
The fifth edition of the "CheckThat! Lab" is one of the 2022 Conference and Labs of the Evaluation Forum (CLEF) and aims to evaluate advances supporting three factuality-related tasks, covering several languages. Our team (SCUoL) participated in task 3A, which concentrates on multi-class fake news detection of English news articles. This paper describes our approach, including several experiments exploring different machine learning and transformer-based models. Furthermore, we employed an additional dataset to support our proposed model. During the validation results phase, the experiments highlight the best performing machine learning classifier, which achieved cross-validation scores of over 60% for the LinearSVC compared to the pre-trained BERT model that exceeds other models in this task. While in the testing results, we obtained an F1 of approximately 0.305 compared to the other participants’ average F1 of 0.252.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2022 Copyright for this paper by its author. This is an open access article under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0) (https://creativecommons.org/licenses/by/4.0/) |
Keywords: | Fake News Detection, Misinformation, Misleading Information, CLEF 20221 , CheckThat! Lab |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 06 Oct 2022 13:27 |
Last Modified: | 06 Oct 2022 13:27 |
Published Version: | http://ceur-ws.org/Vol-3180/ |
Status: | Published |
Publisher: | CEUR Workshop Proceedings |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:191196 |