COVID-19 Fake News Detection With Pre-trained Transformer Models
Abstract
COVID-19 is a new virus that first appeared in the year 2020 and is still currently plaguing our world. With the emergence of this virus, much information, both fake and real, has circulated in the internet. Fake information can lead to misleading information and cause a riot in society. In this paper, we aim to build a hoax detection system using the pre-trained transformer models BERT, RoBERTa, DeBERTa and Electra. From these four models, we will find which model gives the most accurate results. BERT gives a validation accuracy of 97.15% and test accuracy of 97.01%. RoBERTa gives a validation accuracy of 97.34% and test accuracy of 97.15%. DeBERTa gives a test accuracy of 97.48% and a test accuracy of 97.25%. Lastly, Electra gives a validation accuracy of 97.95% and a test accuracy of 97.76%. Electra is one of the newer models and is proven to be the most accurate model in our experiment and the one we will choose to implement fake news detection.
Downloads
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike International License (CC-BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Copyright without Restrictions
The journal allows the author(s) to hold the copyright without restrictions and will retain publishing rights without restrictions.
The submitted papers are assumed to contain no proprietary material unprotected by patent or patent application; responsibility for technical content and for protection of proprietary material rests solely with the author(s) and their organizations and is not the responsibility of the ULTIMATICS or its Editorial Staff. The main (first/corresponding) author is responsible for ensuring that the article has been seen and approved by all the other authors. It is the responsibility of the author to obtain all necessary copyright release permissions for the use of any copyrighted materials in the manuscript prior to the submission.
