Towards intelligent control of influence diffusion in social networks

Control of the flow of information in large-scale non-deterministic social networks is a complex problem requiring both a search for the optimal connection of a control system to the network, and a means of determining the required control signals. This paper formalizes the Network Control Problem (NCP) as a means of relating the field of diverse social network control subproblems. Additionally, this paper defines a novel NCP subproblem, the θ-Consensus Avoidance Problem (θ-CAP), as a next step towards solving the general NCP. Benchmark results for the θ-CAP using Artificial Neural Networks, Evolutionary Neural Networks, and heuristic methods are presented, and interesting areas of the problem space are identified