Community-Aware Prediction of Virality Timing Using Big Data of Social Cascades

Predicting the virality of contents is attractive for many applications in today´s big data era. Previous works mostly focus on final popularity, but predicting the time at which content gets popular (virality timing), is essential for applications such as viral marketing. This work proposes a community-aware iterative algorithm to predict virality timing of contents in social media using big data of user dynamics in social cascades and community structure in social networks. From the continuously generated big data, the algorithm uses the increasing amount of data to make self-corrections on the virality timing prediction and improve its prediction. Experimental results on viral stories from a social network, Digg, prove that the proposed algorithm is able to predict virally timing effectively, with the prediction error bounded within 30% with 20% of data.