SSCA-DRIMP: Semi Supervised Clustering Algorithm for Dynamic Rumor Influence Minimization and Propagation in Social Networks

R. Amutha and Dr.D. Vimal Kumar

The role of online social networks is ever-growing in information sharing. The pros and cons of propagating information sharing are discussed in this proposed work. Here the issues of negative information issues like online rumors are discussed. Currently, Rumor propagation is a sort of social contagion process on facts of certain characteristics. The standstill challenges on rumor propagation have the base facts probability and mobility of characteristics of the user and their rumors. The characteristics of the user and their rumors dose not determine the rumor acceptance probabilities but discovering the similarity among the rumors and non-rumors is crucial in this rumor propagation system. Hence, the proposed work clustering algorithm is developed to solve rumor propagation issue by enhancing Semi Supervised Clustering Algorithm (SSCA). The ultimate rumor propagation results are captured by evaluating the similarity between rumor and normal rumors tweets. SSCA is implemented in sort of modeling the rumor propagation process in social networks. A dynamic Ising propagation model considering both the global popularity and individual attraction of the rumor is presented based on realistic scenario. Based on its intrinsic attributes, the Ising model can be generalized to other similar scenarios. Experiments are implemented based on large-scale real world networks and validate the effectiveness of SSCA-DRIMP algorithm.

Volume 11 | 04-Special Issue

Pages: 1731-1742