Sentiment aware fake news detection on online social networks

Messages posted to online social networks (OSNs) causes a recent stir due to the intended spread of fake news or rumor. In this work, we aim to understand and analyse the characteristics of fake news especially in relation to sentiments, to determine the automatic detection of fake news and rumors. Based on empirical observation, we propose a hypothesis that there exists a relation between a fake message/rumour and the sentiment of the texts posted online. We verify our hypothesis by comparing with the state-of-the-art baseline text-only fake news detection methods that do not consider sentiments. We performed experiments on standard Twitter fake news dataset and show good improvements in detecting fake news/rumor.