| The rapid development of social network brings convenience to people,but also brings massive data,among which maximizing the influence of social networks is a research direction derived from these data.It aims to select the most active node as the initial seed node,and activate more nodes after multiple rounds of propagation.This paper focuses on maximizing the influence of social networks from two different perspectives.The research contents of this paper are as follows:(1)An influence propagation model based on the uncertainty of propagation probability of neighbor nodes is proposed.In the real social networks,the interaction between users is changing dynamically and the propagation probability between users is changing constantly with the interaction,so it is difficult to define the propagation probability between users.It is necessary to measure the propagation probability in the network according to the real situation.Considering the uncertainty of the propagation probability of neighbor nodes,this paper combines the basic IC model and Bayesian theorem,makes an accumulation of the propagation probability and makes corresponding improvement.The experiment on data set shows the advantages of the improved model.(2)An algorithm for maximizing the influence based on the potential activation ability of neighbor nodes is proposed.The algorithm is based on the topological structure of the network and the interactive information of potential value users in the network to measure the potential activation ability of users.The algorithm is tested on two datasets.The results show that the algorithm proposed in this paper can achieve the expected results,and verify the idea of this paper is effective and reasonable.Finally,the algorithm proposed in this paper is performed visualization implementation,which mainly includes the construction of topographic graph and the selection of seed nodes,which vividly shows the process of influencing users in social networks. |
PDF Full Text Request