Learning influence probabilities in social networks
Proceedings of the third ACM international conference on Web search and data mining
Graphical models for game theory
UAI'01 Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence
| Hi-index | 0.00 |
The emergence of online social network platforms enable users to exchange and diffuse information in a more complex way. Different from being just a relay as in traditional diffusion systems, online social network users can even append their ideas on the original message and share to other people when they decide to join the diffusion process. As a result, the users may interact in a different way resulting in a diffusion process different from traditional ones. In this paper, we first collect the data from twitter and observe the diffusion process. Then a graphical game model is introduced to analyze the diffusion system. In our model, we find the Nash equilibrium solutions and discover that users with higher valuation to the original information are welling to make more effort to enrich it. Besides, there are more users choose to join than traditional diffusion schemes. Finally, we apply our model to Twitter social network and find that the official "retweet" wedget decreases the number of contributors but increases the number of participants.