Abstract | ||
---|---|---|
In this paper we propose a belief flow model for social networks and evaluate its application on estimation of public converged beliefs. The model reveals that the control of beliefs in a social network heavily depends on its degree centralities and clustering coefficients. The application of this model to social network belief flow simulation leads to a capacity to control and predict the converged beliefs in a social network. Two different network models, preferential attachment model and generalized Markov Graph model, are applied to the belief flow model. Experiments with published real social network data are provided and demonstrate very good performance of the belief flow model as well as a comparison between different network models. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CAMSAP.2013.6714067 | CAMSAP |
Keywords | Field | DocType |
preferential attachment model,social network belief flow simulation,belief networks,information flow,belief flow model,belief control,machine learning,social networks,generalized markov graph model,graph theory,social networking (online),clustering coefficients,markov processes | Network formation,Network science,Dynamic network analysis,Markov process,Social network,Computer science,Markov chain,Artificial intelligence,Preferential attachment,Network model,Machine learning | Conference |
ISBN | Citations | PageRank |
978-1-4673-3144-9 | 2 | 0.46 |
References | Authors | |
2 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tian Wang | 1 | 21 | 1.79 |
Hamid Krim | 2 | 520 | 59.69 |