A cognitive-inspired algorithm for growing networks

We present models for generating different classes of networks by adopting simple local strategies and an original model of the evolutionary dynamics and growth of on-line social networks. The model emulates people’s strategies for acquiring information in social networks, emphasising the local subjective view of an individual and what kind of information the individual can acquire when arriving in a new social context. We assume that the strategy proceeds through two phases: (a) a discovery phase, in which the individual becomes aware of the surrounding world and (b) an elaboration phase, in which the individual elaborates locally the information trough a cognitive-inspired algorithm. Model generated networks reproduce the main features of both theoretical and real-world networks, such as high clustering coefficient, low characteristic path length, strong division in communities, and variability of degree distributions.