Abstract

The aim of the paper is to identify and categorize frequent patterns describing interactions between users in social networks. We analyze a social network with relationships between users that evolve in time already identified. In our research, we discover patterns based on frequent interactions between groups of users. The patterns are described by the characteristics of these interactions, such as their reciprocity, or the relative difference between estimations of global influences of the users participating in the discussions. The modification of the apriori algorithms is applied as one of the methods for pattern identification. The analyzed social network is built using the data set containing data from the Polish blog website salon24, which concerns mostly socio-political issues.