A Comparative Study on COVID-19 Fake News Detection Using Different Transformer Based Models

TL;DR

This paper compares five transformer-based models for detecting COVID-19 fake news, finding RoBERTa performs best with an F1 score of 0.98, aiding efforts to combat misinformation during the pandemic.

Contribution

It provides a comparative analysis of transformer models for COVID-19 fake news detection, highlighting RoBERTa's superior performance.

Findings

RoBERTa achieved an F1 score of 0.98.

Transformer models vary in effectiveness for fake news detection.

The study demonstrates the potential of transformer models in misinformation mitigation.

Abstract

The rapid advancement of social networks and the convenience of internet availability have accelerated the rampant spread of false news and rumors on social media sites. Amid the COVID 19 epidemic, this misleading information has aggravated the situation by putting peoples mental and physical lives in danger. To limit the spread of such inaccuracies, identifying the fake news from online platforms could be the first and foremost step. In this research, the authors have conducted a comparative analysis by implementing five transformer based models such as BERT, BERT without LSTM, ALBERT, RoBERTa, and a Hybrid of BERT & ALBERT in order to detect the fraudulent news of COVID 19 from the internet. COVID 19 Fake News Dataset has been used for training and testing the models. Among all these models, the RoBERTa model has performed better than other models by obtaining an F1 score of 0.98 in both real and fake classes.