Modeling and Predicting Fake News Spreading on Twitter
share
Fake news becomes a palpable potential risk to society because of the growing use of mobile devices and the immense increase in Internet access across the world. It is essential to develop a simple mathematical model to understand the mechanism of the online dissemination of fake news. In this paper, we propose a point process model for predicting the spreading of the fake news on Twitter. This model describes the cascade as a two-stage process: initially, a cascade spreads as an ordinary news story; a second cascade then emerges through attempts to disclose and rectify the falsity of the news story. We validate this model through the collection of two datasets of fake news cascades from Twitter. We show that the proposed model is superior to the current state-of-the-art methods in accurately predicting the evolution of the fake news cascades. Moreover, the proposed model can appropriately infer the correction time when some users realize the falsity of the news. The proposed model contributes to understand the dynamics of fake news spread in social media and is potentially advantageous in extracting a compact representation of the temporal information of the cascades.
READ FULL TEXT