Research On Restrain Social Network Rumor Based On Rumor Path Tree

Social Networking refers to the social network structure established by interaction among people.From the perspective of sociology,it refers to a network of relationships formed by individuals through realistic social behavior.With the rapid development of the Internet,online social networking has become an indispensable part of people's daily life.At the same time,it has become the most powerful information dissemination platform.Thousands of people can share different information and resources through social network.Unfortunately,except positive news,those platforms become the main channel of spreading misleading information,harmful rumors and even panic messages.Therefore,many Internet users pay close attention to the problem that how to stop the spread of rumors on Social Networking.Among the current methods of restricting the dissemination of rumors,one important way is to set certain specific nodes as a truth campaign.When the truth campaign spreads the truth to other users,the users will distinguish the truth from rumors so that they could immuned the harmful information.However,the existing work lacks of consideration of the limitation of rumors and the weighting of users on Social Networking.In this paper,the author combines the information mechanism of transmission in the real world to simulate the users' behavior online,introduces the concept of entropy and weight in the multi-campaign independent cascade model and constructs a specific propagation model.Driven by the object of minimum quantity of affected nodes in the rumors diffusion cycle,this paper puts forward a solution with two stages to choose top-k node as the campaign of truth.In the first stage,the author calculates the node's risk degree to make clear the risk degree at other nodes taken by rumor nodes in particular moment in propagation range.The second stage is to generate the rumors path tree structure to obtain the propagation path of the rumor.In this structure,the probability of a rumor node reaching the particular rumor node could by calculated.Based on these two parameters,a score function is built to calculate the score of each node;this score represents the sum of all nodes that could be affected by the truth campaign node.After updating all node's score,the option of truth campaign would likely result in some changes of score,we only need to select the node with the highest final score as the truth campaign node,which achieves the goal of minimizing rumor diffusion influence.On the basis of real data,a large number of contrast experiments among datasets argue the effectiveness and efficiency of the method in this paper.