How Predictable is Information Diffusion?

Jake Hofman
Senior Researcher, Microsoft Research in New York City &
Adjunct Assistant Professor of Applied Mathematics, Columbia University,


How does information spread in online social networks and how predictable are online diffusion events? Despite a great deal of existing research on modeling information diffusion and predicting success in social systems, these questions have remained largely unanswered for a variety of reasons, ranging from the inability to observe most word-of-mouth communication to difficulties in precisely and consistently formalizing different notions of success.

This talk will attempt to clarify these issues through an empirical analysis of billions of diffusion events under one simple but unified framework. We will show that despite stable regularities in aggregate diffusion patterns, it remains surprisingly difficult to predict the success of any particular individual or piece of content in an online social network, with our best performing models explaining only half of the empirical variance in outcomes. We conclude by exploring this limit theoretically through a series of simulations that suggest that it is the diffusion process itself, rather than our ability to estimate or model it, that is responsible for this unpredictability.