Fake News Detection Using a Blend of Neural Networks: An Application of Deep Learning

Fake news and its consequences carry the potential of impacting different aspects of different entities, ranging from a citizen’s lifestyle to a country’s global relations, there are many related works for collecting and determining fake news, but no reliable system is commercially available. This study aims to propose a deep learning model which predicts the nature of an article when given as an input. It solely uses text processing and is insensitive to history and credibility of the author or the source. In this paper, authors have discussed and experimented using word embedding (GloVe) for text pre-processing in order to construct a vector space of words and establish a lingual relationship. The proposed model which is the blend of convolutional neural network and recurrent neural networks architecture has achieved benchmark results in fake news prediction, with the utility of word embeddings complementing the model altogether. Further, to ensure the quality of prediction, various model parameters have been tuned and recorded for the best results possible. Among other variations, addition of dropout layer reduces overfitting in the model, hence generating significantly higher accuracy values. It can be a better solution than already existing ones, viz: gated recurrent units, recurrent neural networks or feed-forward networks for the given problem, which generates better precision values of 97.21% while considering more input features.