Exploring reflection of urban society through cyber-physical crowd behavior on location-based social network

Authors:
Shoko Wakamiya;Ryong Lee;Kazutoshi Sumiya
Affiliations:
Graduate School of Human Science and Environment, University of Hyogo, Kobe, Japan;National Institute of Information and Communications Technology, Tokyo, Japan;Graduate School of Human Science and Environment, University of Hyogo, Kobe, Japan
Venue:
DASFAA'12 Proceedings of the 17th international conference on Database Systems for Advanced Applications
Year:
2012

Citing 3
Cited 0

"OMG, from here, I can see the flames!": a use case of mining location based social networks to acquire spatio-temporal data on forest fires

Proceedings of the 2009 International Workshop on Location Based Social Networks
Earthquake shakes Twitter users: real-time event detection by social sensors

Proceedings of the 19th international conference on World wide web
Discovery of unusual regional social activities using geo-tagged microblogs

World Wide Web

Quantified Score

Hi-index	0.00

Visualization

Abstract

Due to the explosive growth of cyber-real space and crowds over the recent social networking sites, the real space in which we are making daily lives is also storongly tied with the imaginary cyber-social space. In this respect, it would be more and more crucial to understand the relationships and the interactions of crowds, physical-real space and cyber-social space. In this paper, we derive images of city in terms of cyber-physical crowds who are nowadays quite common people sharing their lifelogs over social networking sites with location-aware information. Especially, we attempt to explore urban characteristics which are reflected on the social networks through crowd behavior. For this purpose, we model crowd behavior in urban areas by utilizing crowd's daily lifelogs. Then, we explore latent relationships between urban regions and the crowd behavior by means of NMF (Non-negative Matrix Factorization). In the experiment, we show the urban characteristics based on significant crowd behavioral patterns.