Recently there have been significant efforts to mine location-sharing services data and other similar types of geo-social digital data to understand and analyse the complexity of human mobility patterns. Of these studies, very few studies have examined how mobility patterns vary across different regions of the United States. This chapter intends to fill this gap in the literature. Specifically, we use bipartite network modelling to derive a set of metrics for characterizing regional variations in the mobility patterns of individuals. Through this study, we also attempt to gain insight on the types of trips that location-sharing services data may represent. Lastly, we use a community detection to derive information on what we refer to as ‘mobility sheds’. For the purpose of this study, we use a sample of Brightkite location-sharing services data, collected by the Stanford Large Network Dataset collection, SNAP.