Abstract
Location Based Social Networks (LBSNs) have been widely used as a primary data source to study the impact of mobility and social relationships on each other. Traditional approaches manually define features to characterize users' mobility homophily and social proximity, and show that mobility and social features can help friendship and location prediction tasks, respectively. However, these hand-crafted features not only require tedious human efforts, but also are difficult to generalize. In this paper, by revisiting user mobility and social relationships based on a large-scale LBSN dataset collected over a long-term period, we propose LBSN2Vec, a hypergraph embedding approach designed specifically for LBSN data for automatic feature learning. Specifically, LBSN data intrinsically forms a hypergraph including both user-user edges (friendships) and user-time-POI-semantic hyperedges (check-ins). Based on this hypergraph, we first propose a random-walk-with-stay scheme to jointly sample user check-ins and social relationships, and then learn node embeddings from the sampled (hyper)edges by preserving n-wise node proximity (n = 2 or 4). Our evaluation results show that LBSN2Vec both consistently and significantly outperforms the state-of-the-art graph embedding methods on both friendship and location prediction tasks, with an average improvement of 32.95% and 25.32%, respectively. Moreover, using LBSN2Vec, we discover the asymmetric impact of mobility and social relationships on predicting each other, which can serve as guidelines for future research on friendship and location prediction in LBSNs.
Highlights
Understanding the correlation between human mobility and social relationships is crucial for studying human dynamics, which is a key ingredient for friendship and location prediction tasks
We find that node embeddings learnt from 80% social and 20% mobility data results in the best performance on the friendship prediction task, while those learnt from 40% mobility and 60% social data give the best performance on the location prediction task
By revisiting user mobility and social relationships in Location Based Social Networks (LBSNs), we propose LBSN2Vec, a hypergraph embedding approach designed for LBSN data
Summary
Understanding the correlation between human mobility and social relationships is crucial for studying human dynamics, which is a key ingredient for friendship and location prediction tasks. Existing work has shown that considering the correlation between user mobility and social relationships can improve the performance of both friendship prediction [7, 25, 28, 32, 42] and location prediction [8, 12, 18, 21, 25] These approaches usually select a set of hand-crafted features either from user mobility data or from the corresponding social network, and show the impact of one on the other. This graph contains classical edges (i.e., friendships between two users in the social network), and hyperedges (i.e., check-ins linking four nodes, one from each domain, representing a user’s presence at a POI at a specific time along with the semantic information about the user’s activity there). Our LBSN2Vec can model the impact of user mobility and social relationships on each other
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
