Automatic Twitter Rumour Detection using Machine Learning

Information generation and its dissemination increases day by day on a very large scale as the count of users increase on social media. These platforms are a stage for the people to exchange their ideas and opinions. Social media microblogging platform (ex. Twitter) is the go-to place in case of discussion about any important event. Information spreads at a lightning pace on twitter. This leads to rapid spread of false information i.e. rumours which can cause a feeling of unrest among the people. Hence, it is crucial to analyze and verify the degree of truthfulness of such content. The automatic detection of rumours in its initial stages is a challenge because of the complexity of the text. In this paper, we have implemented and compared different existing machine learning algorithms on the PHEME dataset to identify and detect the rumours. The performance of the models has been analyzed.