The community detection microservice helps in deeper network understand-
ing and reveals interesting properties shared by the members. We propose a novel approach that combines event clustering and link analysis to detect communities along with clustering users into overlapping communities via agent, role, stage discovery microservices.
The reputation calculation microservice estimates users’ trustworthiness considering various conflicting parameters, such as accuracy, timeliness, latency, and high anonymity preservation.
The role discovery microservice labels anonymous users with individual roles which are important for classification, e.g. the role father in the concept family.
The semantic linking microservice helps to explicitly state implicit connections between users by analyzing extensive and repeated interactions. The explicit information about links will then be the basis for all further reasoning, classification and intelligence.
