Detecting large reshare cascades is an important problem in online social networks. There are a variety of attempts to model this problem, from using time series analysis methods to stochastic processes. Most of these approaches heavily depend on the underlying network features and use network information to detect the virality of cascades. In most cases, however, getting such detailed network information can be hard or even impossible.
In contrast, in this paper, we propose SansNet, a network agnostic approach instead. Our method can be used to answer two important questions: (1) Will a cascade go viral? and (2) How early can we predict it? We use techniques from survival analysis to build a supervised classifier in the space of survival probabilities and show that the optimal decision boundary is a survival function. A notable feature of our approach is that it does not use any network-based features for the prediction tasks, making it very cheap to implement. Finally, we evaluate our approach on several real-life data sets, including popular social networks like Facebook and Twitter, on metrics like recall, F-measure and breakout coverage. We find that network agnostic SansNet classifier outperforms several non-trivial competitors and baselines which utilize network information.