How much can social metrics actually help in content distribution?
by Ioannis Stavrakakis (National & Kapodistrian University of Athens, Greece)
Abstract:
Social metrics have recently been employed to capture the degree of similarity and potential for encounters between mobile nodes, as well as assess the nodes’ “standing” within a community or network. In this talk some recent works-examples are briefly presented showing the potential benefits from incorporating social metrics in content placement, replication and routing. Weaknesses associated with these social metrics are also discussed and an experimental study - based on “CRAWDAD data set cambridge/haggle (v. 2009-05-29)” - is presented pointing to inherent weaknesses and inefficiencies associated with centrality-based routing approaches.
