Name
Abstract | ||
|---|---|---|
Social influence analysis has become one of the most important technologies in modern information and service industries. Thus, how to measure social influence of one user on other users in a mobile social network is also becoming increasingly important. It is helpful to identify the influential users in mobile social networks, and also helpful to provide important insights into the design of social platforms and applications. However, social influence modeling is an open and challenging issue, and most evaluation models are focused on online social networks, but fail to characterize indirect influence. In this paper, we present a mechanism to quantitatively measure social influence in mobile social networks. We exploit the graph theory to construct a social relationship graph that establishes a solid foundation for the basic understandings of social influence. We present an evaluation model to measure both direct and indirect influence based on the social relationship graph, by introducing friend entropy and interaction frequency entropy to describe the complexity and uncertainty of social influence. Based on the epidemic model, we design an algorithm to characterize propagation dynamics process of social influence, and to evaluate the performance of our solution by using a customized program on the basis of a real-world SMS/MMS-based communication data set. The real world numerical simulations and analysis show that the proposed influence evaluation strategies can characterize the social influence of mobile social networks effectively and efficiently. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1016/j.ins.2016.08.023 | Information Sciences |
Keywords | Field | DocType |
Mobile social networks,Social influence,Information entropy,social relationship graph,Direct influence,Indirect influence | Graph theory,Information theory,Social network,Mobile social network,Computer science,Exploit,Social influence,Artificial intelligence,Entropy (information theory),Social heuristics,Machine learning | Journal |
Volume | ISSN | Citations |
379 | 0020-0255 | 39 |
PageRank | References | Authors |
0.97 | 31 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sancheng Peng | 1 | 234 | 19.59 |
| Aimin Yang | 2 | 48 | 3.09 |
| Lihong Cao | 3 | 59 | 3.65 |
| Shui Yu | 4 | 2365 | 208.84 |
| Dongqing Xie | 5 | 277 | 24.78 |