A model for analyzing dynamic social networks using system dynamics

One main problem in organizations is the lack of timely detection of large-scale changes such as crises. Detecting the changes is always delayed. One way to detect a crisis in an organization is to examine and analyze the social network of the employees. The models used so far in this field are generally graph-based and use the assumption of heterogeneity of nodes. Such models are not capable of modeling dynamic behaviors due to the static nature of the graphs. So far, no study has been found on the system dynamics approach in analyzing the behavior of longitudinal social networks. In order to fill this research gap, in this paper, using the system dynamics framework, dynamic social network modeling is done by considering the heterogeneity behavior of nodes. In this method, stochastic differential equation is used to simulate the collective behavior of nodes and to highlight the stochasticity of dynamic social networks. This modeling is simulated in Vensim software. In order to validate the proposed model, this modeling has been evaluated on Enron's communication network. Then, by examining the simulation scenarios and variables, it was found that the volatility rate or standard deviation of the data is a key variable in social networks. The results of this study provide a model of social media behavior in different situations for decision makers and planners.