final.2.pdf (558.26 kB)
Download file

Modeling Information Diffusion over Social Networks for Temporal Dynamic Prediction

Download (558.26 kB)
journal contribution
posted on 16.02.2018, 15:02 by Dong Li, Shengping Zhang, Xin Sun, Huiyu Zhou, Sheng Li, Xuelong Li
Modeling the process of information diffusion is a challenging problem. Although numerous attempts have been made in order to solve this problem, very few studies are actually able to simulate and predict temporal dynamics of the diffusion process. In this paper, we propose a novel information diffusion model, namely GT model, which treats the nodes of a network as intelligent and rational agents and then calculates their corresponding payoffs, given different choices to make strategic decisions. By introducing time-related payoffs based on the diffusion data, the proposed GT model can be used to predict whether or not the user's behaviors will occur in a specific time interval. The user's payoff can be divided into two parts: social payoff from the user's social contacts and preference payoff from the user's idiosyncratic preference. We here exploit the global influence of the user and the social influence between any two users to accurately calculate the social payoff. In addition, we develop a new method of presenting social influence that can fully capture the temporal dynamics of social influence. Experimental results from two different datasets, Sina Weibo and Flickr demonstrate the rationality and effectiveness of the proposed prediction method with different evaluation metrics.

Funding

D. Li was supported in part by the Hong Kong Scholar Foundation of China (No. ALGA4131016116), the China Postdoctoral Foundation (No. 2016M600250), and the Major Science and Technology Foundation of Shandong Province (No. 2015ZDXX0201B02). S. Zhang was supported in part by the Natural Science Foundation of China (No. 61672188). X. Sun was supported in part by the Natural Science Foundation of China (No. 61602128) and the Natural Science Foundation of Shandong Province (No. ZR2016FQ13). H. Zhou was supported in part by UK EPSRC under Grants EP/N508664/1 and EP/N011074/1, and Royal SocietyNewton Advanced Fellowship under Grant NA160342. X. Li was supported in part by the National Natural Science Foundation of China (Grant No. 61761130079).

History

Citation

IEEE Transactions on Knowledge and Data Engineering, 2017, 29 (9), pp. 1985-1997 (13)

Author affiliation

/Organisation

Version

AM (Accepted Manuscript)

Published in

IEEE Transactions on Knowledge and Data Engineering

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

issn

1041-4347

eissn

1558-2191

Acceptance date

20/04/2017

Copyright date

2017

Available date

16/02/2018

Publisher version

http://ieeexplore.ieee.org/document/7921565/

Language

en