Identification of Influential Spreaders in Geo-social Network

Identifying influential nodes in multilayer networks, such as networks in an LBSN, has attracted much attention because of its great theoretical significance and wide application. Existing methods are limited to a single network and don't consider some social environmental factors, such as social constraints and human motion. In this paper, firstly, we propose a geo-social multilayer with two layers including the online social network and geographic co-location weighted network. In this multilayer networks, the mutual user influence is calculated. Then, by comparing and analyzing the same influential spreaders on geo-social network, we seek a possible way to find influential nodes by combing social relationships and individual behaviors. Finally, Susceptible - Infected-Recovered (SIR) model is used to evaluate the ability to spread nodes. The experimental results show that our method is effective for detecting the node influence and the geographic influence is stronger than social influence.