Name
Abstract | ||
|---|---|---|
Being a leading location-based social network (LBSN), Foursquare's Swarm app allows users to conduct check-ins at a specified location and share their real-time locations with friends. This app records a massive set of spatio-temporal information of users around the world. In this paper, we track the evolution of user density of the Swarm app in New York City (NYC) for one entire week. We study the temporal patterns of different venue categories, and investigate how the function of venue categories affects the temporal behavior of visitors. Moreover, by applying time-series analysis, we validate that the temporal patterns can be effectively decomposed into regular parts which represent the regular human behavior and stochastic parts which represent the randomness of human behavior. Finally, we build a model to predict the evolution of the user density, and our results demonstrate an accurate prediction. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/PERCOMW.2018.8480234 | 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) |
Keywords | Field | DocType |
Mobile Data Sensing,Location Based Social Networks,Spatial and Temporal Analysis,Swarm> | Data mining,User density,Social network,Swarm behaviour,Computer science,Swarming (honey bee),Randomness,Distributed computing | Conference |
ISSN | ISBN | Citations |
2474-2503 | 978-1-5386-3228-4 | 0 |
PageRank | References | Authors |
0.34 | 3 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hao Zhao | 1 | 27 | 11.64 |
| Qingyuan Gong | 2 | 2 | 1.72 |
| Yang Chen | 3 | 375 | 33.50 |
| Jingrong Chen | 4 | 0 | 0.34 |
| Yong Li | 5 | 2972 | 218.82 |
| Xiaoming Fu | 6 | 1594 | 126.46 |