Research On Social Network Information Dissemination Mechanism Based On User Characteristics

With the rapid expansion of netizens and the widespread popularity of mobile terminal devices,major social platforms have accumulated a large number of users,and netizens are more inclined to disseminate information in virtual networks,real-time communication between users and strong communication on social networks will form different user groups into different information dissemination networks.However,online social networks and various social platforms provide convenience to people’s lives,but also bring many social problems,such as the deterioration of the network environment and the wanton dissemination of negative information.Exploring the underlying evolutionary laws and communication modes in the information dissemination network,and analyzing the factors that affect the speed and scale of information dissemination are important prerequisites for governing the social network environment.It also has important reference significance for predicting the scale and efficiency of microblog topic dissemination.In general,the research content of this article is as follows:First,based on the information dissemination process of online social networks,this paper adds weak immune nodes and immune nodes on the basis of the classic infectious disease model SIR,and builds an improved information dissemination model SEIRO.The model takes into account the information recipients and information provided in social information dissemination.The trust relationship between disseminators and topics in online social platforms are in their communication life cycle,and the user’s interest will decrease non-linearly as the number of disseminators increases.Secondly,according to the model,the corresponding dynamic differential equation is established,the balance point and the propagation threshold of the model are solved,and the internal mechanism of the propagation threshold is explored and analyzed.In Matlab R2019a software,the online social network information dissemination model of this article is simulated and analyzed,which mainly includes the stability analysis of the model,that is,the influence mechanism of each factor on the maximum value of each state node,and then the sensitivity analysis is performed on each of the models.The parameters are adjusted and analyzed to explore the influence of the factor size on the process of model information propagation under different conditions.Finally,the model is analyzed and verified by using web crawler technology to capture the negative topic communication data in the Weibo platform,such as the number of likes,comments,and favorites,and then divide the topic life cycle into incubation period,growth period,and maturity according to its popularity.In the four stages of period and decline period,compare the error between the simulation results of the node data of the SEIRO and SIR models and the actual data in each period.The study found that the model has a zero-propagation equilibrium point and an internal equilibrium point.The model is locally stable at the zero-propagation equilibrium point,and the internal equilibrium point is locally asymptotically stable in the model;the change in the propagation efficiency between each node has a different maximum value of the node The maximum value of the latent person is smaller than that of the weakly immune person and the communicator.There will be a certain degree of user loss in the conversion process;the degree of trust between users is directly proportional to the efficiency of information dissemination,and the user’s interest in information attenuation coefficient It is inversely proportional to the dissemination efficiency,that is,the user’s interest in information decreases with the increase in the number of topic disseminations;the model in this study is closer to the actual data than the simulation result of the SIR model,and is more reasonable and reliable,and it also provides information dissemination trend judgment It provides an important basis for the monitoring and management of the network health virtual environment.