ABSTRACT
There have been a rampant spread of fake news during the COVID-19 pandemic. Unverified cures generated from fake news pose a threat to public health. The hoax messages can downplay the seriousness of the situation leading to a subsequent ignorance of basic guidelines like masks mandates and social distancing. Hence, it is necessary to curb the spread of such news and misinformation which can cause public harm. This paper proposes a counteractive measure to mitigate the aforementioned fake news by constructing a dataset compiled from verified fact-checking websites and news resources. In this paper, Machine Learning algorithms such as Logistic Regression, Naive Bayes, etc. and Deep Learning models such as Recurrent Neural Networks have been applied to the dataset and trained models provide promising benchmark results. © 2021 IEEE.