Abstract
False data in network big data has led to considerable ineffectiveness in perceiving the property of fact. Correct conclusions can be drawn only by accurately identifying and eliminating these false data. In other words, analysis is the premise to reaching a correct conclusion. This paper develops a big data network dissemination model based on the properties of the network. We also analyze the attributes of the big data random complex network based on the revised F-J model. Then, based on the scale-free nature of network big data, the evolution law of connected giant components and Bayesian inference, we propose an identification method of effective data in networks. Finally, after obtaining the real data, we analyze the dissemination and evolution characteristics of the network big data. The results show that if some online users intentionally spread false data on a large-scale website, the entire network data becomes false, despite a minimal probability of choosing these dissemination sources.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have