Application of deep learning algorithms detecting fake and correct textual or verbal news

Abstract

Abstract. The ongoing spread and expansion of information technology and social media sites have made it easier for people to access different types of news – political, economic, medical, social, etc. through these platforms. However, this rapid growth in news outlets and the demand for information has blurred the lines between real and fake news and led to the dissemination of fake news, which is a dangerous state of affairs.
The outbreak of the coronavirus pandemic and awareness of the threats posed all across the globe. And a parallel rise in fake news and rumors, like unsubstantiated statements and deceptive ideas, were noticed. The main aim of this study is supposed to set out to overcome these kinds of problems in the future with the application of deep learning algorithms (LSTM, Bi-LSTM, BERT), using a large dataset (39279 rows) to identify fake and correct textual or verbal news. The results of the deep learning application using different algorithms show that the BERT model performed the best, achieving a text classification accuracy of 96.63 %.