Application of Machine Learning Algorithm for Classification of Fake COVID-19 Tweets

Abstract

The intentional dissemination of false information, known as fake news, aims to manipulate readers into accepting biased or untrue beliefs by altering their interpretation and response to real news. However, identifying fake news is a tedious task, especially on platforms like Twitter where information is rapidly disseminated. Therefore, Machine Learning classifiers can be leveraged to detect fake news with a higher accuracy. The novelty of Corona Virus Disease 2019 has made it hard to identify a widely accepted dataset for fake news detection. Recently, a more robust and up-to-date dataset called FND Dataset was created by scraping tweets from health organizations' Twitter accounts using Twitter API and socialscrapr. The dataset was processed using Python libraries and Microsoft Excel before being split into training, validation, and testing datasets. SVM, LR, and DT baseline Machine Learning algorithms were utilized, with the SVM classifier achieving the best performance for accuracy and F1-Score metrics as 93.17%.