Applications of Recurrent Neural Network in Fake News Classification

Abstract

In communication, the explosive growth of social networking sites has made it easier for people to share and receive information. However, besides the benefits brought, this environment creates favorable conditions for fake news to spread quickly and have a significant impact on the socio-economic situation. In recent years, research results in the field of natural language processing have achieved many achievements with the use of deep learning models, especially recurrent neural networks (RNNs) or contextual language synthesis model (BERT). From the above practices, we choose to study the application of recurrent neural networks in detecting and classifying Vietnamese fake news. This paper presents the research results on building and testing a tool to support detecting and classifying fake news in Vietnamese. The main contents presented in this paper are related to fake news classification, Word Embedding, recurrent neural networks and BERT.