Abstract

We consider two distinct types of online social network, the first made up of a log of writes to wall by users in Facebook, and the second consisting of a corpus of emails sent and received in a corporate environment (Enron). We calculate the statistics which describe the topologies of each network represented as a graph. Then we calculate the information loss and risk of disclosure for different percentages of perturbation for each dataset, where perturbation is achieved by randomly adding links to the nodes. We find that the general tendency of information loss is similar, although Facebook is affected to a greater extent. For risk of disclosure, both datasets also follow a similar trend, except for the average path length statistic. We find that the differences are due to the different distributions of the derived factors, and also the type of perturbation used and its parameterization. These results can be useful for choosing and tuning anonymization methods for different graph datasets.