Towards intelligent control of influence diffusion in social networks

Evolving Neurocontrollers for the Control of Information Diffusion in Social Networks

“…In [4], the θ-Consensus Avoidance Problem (θ-CAP) is defined as an NCP subproblem with both configuration and behavioural search requirements. In addition to considering the optimal configuration required to deliver appropriate control signals, the θ-CAP considers the dependent search for a state-to-signal mapping capable of maintaining an equilibrium of node states within the network.…”

“…Results from [4] demonstrate that an EANN control system is capable of consistently learning network balancing behaviour over a variety of random control system configurations and network types. Additionally, the Anti-Majority (AM) control system showed results competitive to the EANN over select problem instances of lower budget.…”

On The Control Of Opinion In Social Networks

“…The concept of social network control is formalized in the Network Control Problem (NCP). The NCP formalization (see Chapter 3, [102]) defines a pair of dependent optimization subproblems in terms of discovering both the structural and behavioural components of a control system. The objective of the control system is to guide the state of the social network via interactions at the node-state level.…”

“…The θ-CAP is defined as an NCP instance with both configuration and behavioural search requirements (see Chapter 4 [102]). In addition to considering which nodes to direct, the control system must also determine the step by step instructions it will give.…”

On Behaviour-Based Network Inference and Distribution-Based Network Control

“…however, this is not the only possible view of network control. More recent work within the network control domain (e.g., Runka, 2016;Runka and White, 2015a;McKenney and White, 2016) has considered the behavioural aspects present within many networked systems, directing the focus toward a more practical view of network control. This opens up the possibility of many different types of network control problems involving failure avoidance, the limitation of state change, or other control goals.…”