Facebook feedback capacity modeling

The internal feedback structure exists in non-hierarchical complex networks in the form of cycles. Diffusion of information from a node to reach out all the rest occurs through penetration layers (depths). The information credibility or accuracy may be challenged in each layer due to internal feedback loops. In this work, we study feedback diffusion capacity and analyze existing patterns of relationships and ties among complex networks entities to find how the feedback of information is diffused and propagated through the network. As the information propagates to subsequent layers, on average, the feedback density heterogeneity in complex networks reaches saturation after the third penetration in random and scale-free networks. The maximum penetration defines the feedback capacity of the network. The experiment results show that in the third and in most networks the fifth penetration depth covers almost 90 % of the nodes. In the small-world networks, the feedback capacity is dynamic and continue increasing as the network size increases. Small-world network has the best feedback capacity among networks configuration. A case study on real Facebook network shows a feedback capacity that resembles random networks.