Fake News Detection and Classification with Recurrent Neural Network Based Deep Learning Approaches

Abstract

Events happening in the world are transmitted to the end user through the news channel. The information transmitted from the news is generally considered to be accurate. However, there may be errors or lies in the information that circulates on the news channels. At the same time, this news has an impact on serious environments, such as the economy. In social networks where data sharing is increasing, news data is piling up uncontrollably. In these data piles, there is real information as well as different information that is not real commercial, political, or sales-orientated. False information and data expand faster as a result of sharing false information by users. This news directly affects users, causing erroneous transactions, misinformation, or financial loss. For the stated reasons, automatic fake news classification systems are proposed in this article by combining natural language processing with Recurrent Neural Network (RNN) based deep learning methods. The proposed systems were tested on a dataset containing 23,481 fake news and 21,417 real news using general performance metrics. As a result of the test processes, the proposed BiLSTM method provided 99,72% accuracy, while the proposed GRU method accessed 97,50% accuracy.