PROJECT TITLE :

Modeling Information Diffusion over Social Networks for Temporal Dynamic Prediction - 2017

ABSTRACT:

Modeling the process of knowledge diffusion may be a challenging downside. Although numerous tries are created so as to unravel this downside, very few studies are actually in a position to simulate and predict temporal dynamics of the diffusion process. During this paper, we have a tendency to propose a completely unique info diffusion model, specifically GT model, that treats the nodes of a network as intelligent and rational agents and then calculates their corresponding payoffs, given totally different choices to create strategic choices. By introducing time-connected payoffs based mostly on the diffusion data, the proposed GT model will be used to predict whether or not the user's behaviors can occur during a specific time interval. The user's payoff will be divided into two elements: social payoff from the user's social contacts and preference payoff from the user's idiosyncratic preference. We here exploit the world influence of the user and therefore the social influence between any two users to accurately calculate the social payoff. Yet, we develop a new technique of presenting social influence which will absolutely capture the temporal dynamics of social influence. Experimental results from 2 completely different datasets, Sina Weibo and Flickr demonstrate the rationality and effectiveness of the proposed prediction methodology with completely different evaluation metrics.