Modeling the Clustering Structure of Complex Networks and Calculating Propagation Thresholds for Bandwagon Behavior of Social Media Papers from the Perspective of Knowledge Reproduction and Anti-Regulatory Discipline

This paper constructs a heterogeneous network adjacency matrix containing multiple user relationships from the connotation of professional organizations and other guides to individual behaviors covered by the take-read mechanism.The GAT algorithm is used to learn the embedding of its heterogeneous network in order to obtain the embedding vectors of user nodes, which serves as the basis for the analysis of the spreading influence of group behavior.An event recognition method based on word embedding and hierarchical cohesive clustering is proposed to analyze the recognition and evolution of social media essay-carrying behavioral events (group behavioral events) for complex networks.We point out that the distribution of group behavior affects the dynamics of information dissemination, set the adoption threshold parameter of the group, and analyze the dissemination pattern of individuals' (individual information) participation in essay-reading behaviors.Analyze the emergence and evolution of thesis-reading behavior in social media, and explore the influence of individual's own attributes and the attitude of neighboring nodes on the evolution of group behavioral events in complex networks.The spreading degree analysis is conducted for different relational social media bandwagon behaviors.When , i j I =0.6 and , i j Ex =0.8, the individual's decision is supported by the neighbor's viewpoints, and the users who have already participated in the paper band-reading activities have a strong attraction to the individual.When the strong degree increases to a certain value, the individual decides to participate in the dissertation banding activity, at which point the individual is no longer influenced by the external environment.The degree of the initial node for the propagation of thesis banding behavior in random networks and small-world networks is linearly and negatively correlated with the percentage of the information audience.