On the statistical properties of viral misinformation in online social media
arXiv:1609.09435 · doi:10.1016/j.physa.2016.11.012
Abstract
The massive diffusion of online social media allows for the rapid and uncontrolled spreading of conspiracy theories, hoaxes, unsubstantiated claims, and false news. Such an impressive amount of misinformation can influence policy preferences and encourage behaviors strongly divergent from recommended practices. In this paper, we study the statistical properties of viral misinformation in online social media. By means of methods belonging to Extreme Value Theory, we show that the number of extremely viral posts over time follows a homogeneous Poisson process, and that the interarrival times between such posts are independent and identically distributed, following an exponential distribution. Moreover, we characterize the uncertainty around the rate parameter of the Poisson process through Bayesian methods. Finally, we are able to derive the predictive posterior probability distribution of the number of posts exceeding a certain threshold of shares over a finite interval of time.
References in corpus (17)
- Science vs Conspiracy: collective narratives in the age of (mis)information
- Virality Prediction and Community Structure in Social Networks
- Computational fact checking from knowledge networks
- Hoaxy: A Platform for Tracking Online Misinformation
- Users Polarization on Facebook and Youtube
- Emotional Dynamics in the Age of Misinformation
- Trend of Narratives in the Age of Misinformation
- On the statistical properties and tail risk of violent conflicts
- Social Influences in Opinion Dynamics: the Role of Conformity
- Are your data really Pareto distributed?
- Towards Detecting Rumours in Social Media
- Network Strategies in Election Campaigns
- Exploring Image Virality in Google Plus
- Debunking in a World of Tribes
- Social determinants of content selection in the age of (mis)information
- Collective attention in the age of (mis)information
- Early Warning of Human Crowds Based on Query Data from Baidu Map: Analysis Based on Shanghai Stampede