Rooting our Rumor Sources in Online Social Networks: The Value of Diversity From Multiple Observations

This paper addresses the problem of rumor source detection with multiple observations, from a statistical point of view of a spreading over a network, based on the susceptible-infectious model. For tree networks, multiple independent observations can dramatically improve the detection probability. For the case of a single rumor source, we propose a unified inference framework based on the joint rumor centrality, and provide explicit detection performance for degree-regular tree networks. Surprisingly, even with merely two observations, the detection probability at least doubles that of a single observation, and further approaches one, i.e., reliable detection, with increasing degree. This indicates that a richer diversity enhances detectability. Furthermore, we consider the case of multiple connected sources and investigate the effect of diversity. For general graphs, a detection algorithm using a breadth-first search strategy is also proposed and evaluated. Besides rumor source detection, our results can be used in network forensics to combat recurring epidemic-like information spreading such as online anomaly and fraudulent email spams.