Abstract
We study the problem of detecting hierarchical ties in a social network by exploiting the interaction patterns between the actors (members) involved in the network. Motivated by earlier work using a rank-based approach, i.e., Rooted-PageRank, we introduce a novel time-sensitive method, called T-RPR, that captures and exploits the dynamics and evolution of the interaction patterns in the network in order to identify the underlying hierarchical ties. Experiments on two real datasets demonstrate the performance of T-RPR in terms of recall and show its superiority over a recent competitor method.