基于信息风险感知理论的虚假信息点对点传播建模与仿真研究

Modeling and Simulation of Point-to-Point Propagation of False Information Based on Information Risk Perception

在计算社会科学研究中,受传染病启发的传播模型被广泛用于模拟虚假信息传播,但传统的传染病模型不区分个体间的差异。现实世界中,个体间的差异有助于理解虚假信息如何在个体间传播,这对于探究社交网络中虚假信息的传播规律、抑制虚假信息的传播具有重要意义。文中基于信息风险感知理论,利用在线社交用户的情绪、知识水平、信任度和媒体的接触数量等对传播个体的差异加以区分,构建更加符合现实的虚假信息点对点传播模型。在传播过程中,个体间的差异表现为不同的传播概率,高传播概率的个体更容易转化为传播状态,同时使用人工标注的Facebook数据集进行仿真模拟来研究虚假信息的传播规律。结果发现,相比平均概率传播系统,在点对点传播模式下传播虚假信息的时间跨度更长,波及范围更广。此外,通过控制高传播概率节点,能够实现对虚假信息传播的事前控制,且其相比随机控制、控制高影响力节点的方法取得了更好的效果,但依次增加节点控制比例并未按照预想得到更好的控制效果,出现了“反常识”的特征。

In the study of computational social science,the propagation model inspired by infectious diseases is widely used to simulate the spread of false information.However,the traditional infectious disease model does not distinguish the differences among individuals.In the real world,the difference between individuals helps to understand how false information spreads between individuals,which is of great significance for exploring the propagation law of false information in social networks and suppressing the spread of false information.Based on the information risk perception theory,this paper makes use of online social users’emotion,knowledge level,trust and the number of media contacts to distinguish the differences of communication indivi-duals,and builds a more realistic point-to-point communication model of false information.In the process of communication,the differences between individuals are manifested in different communication probabilities.Individuals with high communication probabilities are more likely to be transformed into communication states.This paper uses the manually annotated Facebook data set to conduct simulation to study the propagation laws of false information.The results show that,compared with the average probability propagation system,the time span of spreading false information in the point-to-point propagation mode will be longer and the coverage will be wider.In addition,by controlling the nodes with high propagation probability,it is possible to control the propagation of false information in advance,and it has achieved better results than the methods of random control and controlling the nodes with high influence.However,increasing the control proportion of nodes in turn can not achieve better control results as expected,and the characteristics of“anti common sense”appear.