A new method for community detection in social networks based on message distribution (2011.12685v1)

Abstract: Social networks are the social structures which are composed of people and their relationships and nowadays, play an important role in data extension. In such networks, the communities are recognized as the groups of users who are often interacting with each other. In this article, a method will be introduced for community detection, which has the capability of adoption with different kinds of social networks and also is synchronized with the actual world. One of the most important defined parameters in this paper is the rate of the transferred messages between the nodes of the network, this parameter would be dynamically investigated. In this strategy, the network is reviewed in different time intervals, and the inter-node relations are enhanced or weakened. Therefore, the topology of the network is continuously changing in response to the behavior of the users. The defined parameters in the proposed algorithm are capable of adopting with different types of the social networks and a weight will be assigned to every parameter which is indicative of the relative importance of that parameter in comparison with the other ones. The obtained results show that this method, in comparison with the similar methods, leads to achievement of the desirable results.