Paper Title
Covid-19 Fake News Detection on Twitter

Abstract
In relation to the spread of COVID-19 worldwide since 2020, the occurrence and rapid spread of false and misleading information on social media, called fake news, is becoming a problem of alarming proportions. This paper deals with the identification of COVID-19 fake news in large body of tweets. We present the results obtained by several machine learning models, such as Random Forests, Support Vector Machines, Logistic Regression, KNeighbors classifier, Gradient Boosting, and Deep Neural Network. The “COVID-19 Twitter Fake News” dataset containing 2,000 genuine tweets and 2,000 fake tweets about COVID-19 is used for classification. The results produced by our machine learning models are superior to those of the cross-stitch semi-supervised neural attention machine learning model on the same dataset. In particular, the F-measure exceeds 93% and the True Negative Rate is more than 91% in all the models. Keywords - Machine Learning, Supervised Learning, Twitter, Fake news