Today, the churn phenomenon has been considered in many applications as an important outcome. Social networks can be considered as one of the most important applications with the mentioned outcome. Churn in social networks depends on the users' activity in a communication environment and appears if this activity is less than a required extent. Swarm Intelligence algorithms(SI), assumed to be the proper tools to model the communications in a social network. This bunch of algorithms according to the local agents' behavior, try to result the global behavior. This paper aims to measuring the user's churn by the mentioned method and including the communication messages transferred by the users in the network. Considering the measured activity rate, a churn threshold in various areas of communication will be obtained. Simulation results referring to confirmed the presented model of communication. The model validation and other values are obtained by a discrete event simulator. The communications used in this simulation result from mining a data set including real communications for one species of the mentioned networks.