Where You Go Reveals Who You Know: Analyzing Social Ties from Millions of Footprints

This paper aims to investigate how the geographical foot-prints of users correlate to their social ties. While conven-tional wisdom told us that the more frequently two users co-locate in geography, the higher probability they are friends, we find that in real geo-social data, Gowalla and Meetup, al-most all of the user pairs with friendships had never met ge-ographically. In this sense, can we discover social ties among users purely using their geographical footprints even if they never met? To study this question, we develop a two-stage feature engineering framework. The first stage is to charac-terize the direct linkages between users through their spatial co-locations while the second is to capture the indirect link-ages between them via a co-location graph. Experiments conducted on Gowalla check-in data and Meetup meeting events exhibit not only the superiority of our feature model, but also validate the predictability (with 70 % accuracy) of detecting social ties solely from user footprints. 1