G GeoSocial Data Analytics

The ubiquity of mobile devices has enabled Location-Based Social Networks (LBSN), such as Foursquare and Twitter, to collect large datasets of people’s locations, which tell who has been where and when. Such a collection of people’s locations over time (aka spatiotemporal data) is a rich source of information for studying various social behaviors. One particular behavior that has gained considerable attention in research and has numerous online applications is whether social relationships among people can be inferred from spatiotemporal data and how to estimate the strength of each relationship quantitatively (aka social strength). The intuition is that if two people have been to the same places at the same time (aka co-occurrences), there is a good chance that they are socially related. Thus, the goal is to derive the implicit social network of people and the social strength from their real-world location data as opposed to or in addition to their online activities. Social strength is a quantitative measure between 0 and 1, which shows the extent two people are socially related. The 0 value indicates the absence of a relationship, while 1 indicates the closest possible relationship between two individuals.