Analysis of User Behavior in Mobile Internet Using Bipartite Network

With the popularization of mobile network and smart phone, the number of mobile Internet users has been growing rapidity and various kinds of services have emerged. It is significant for both academia and industries to understand its user behavior. This paper firstly constructs a user-service weighted bipartite network model, according to the methodology in complex network, and then groups the present services in mobile Internet into 12 categories, in order to research user access characteristics for different kinds of services. Using this model, we analyze the user behavior mainly from user interest range, user interest intensity, user access characteristics and user access relevance four aspects. Our click stream data sets, which contain two 1-week periods, one is in 2010 and the other in 2011, were collected from a WAP gateway of one main Mobile Telecom Carrier in Chongqing Province, China, then, based on the two data sets, we show the characteristics of service access behavior and expose the changes of user behavior during two years.