Toward Automatic Fake News Classification

Abstract

The interaction of technology with humans have many adverse effects. The rapid growth and outreach of the social media and the Web have led to the dissemination of questionable and untrusted content among a wider audience, which has negatively influenced their lives and judgment. Different election campaigns around the world highlighted how ''fake news'' - misinformation that looks genuine - can be targeted towards specific communities to manipulate and confuse them. Ever since, automatic fake news detection has gained widespread attention from the scientific community. As a result, many research studies have been conducted to tackle the detection and spreading of fake news. While the first step of such tasks would be to classify claims associated based on their credibility, the next steps would involve identifying hidden patterns in style, syntax, and content of such news claims. We provide a comprehensive overview of what has already been done in this domain and other similar fields, and then propose a generalized method based on Deep Neural Networks to identify if a given claim is fake or genuine. By using different features like the authenticity of the source, perceived cognitive authority, style, and content-based factors, and natural language features, it is possible to predict fake news accurately. We have used a modular approach by combining techniques from information retrieval, natural language processing, and deep learning. Our classifier comprises two main sub-modules. The first sub-module uses the claim to retrieve relevant articles from the knowledge base which can then be used to verify the truth of the claim. It also uses word-level features for prediction. The second sub-module uses a deep neural network to learn the underlying style of fake content. Our experiments conducted on benchmark datasets show that for the given classification task we can obtain up to 82.4% accuracy by using a combination of two models; the first model was up to 72% accurate while the second model was around 81\% accurate. Our detection model has the potential to automatically detect and prevent the spread of fake news, thus, limiting the caustic influence of technology in the human lives.