Hidden Community Mining under the RST/POSL Framework
Hong Feng Lai · 2009
The social network analysis (SNA) attempts to find explicit similarities between actors in the network. Traditional clustering methods are based on the attributes between actors in the network that lacks for logic foundation. In this paper we apply rough set theory to SNA. Objects are partitioned into equivalence classes interpreting the hidden community. This paper proposes a framework to find the implicit social network based on RST (rough set theory) and POSL to extract and express the social structure and relationship in diverse databases. The interface of different level is a mapping from a source model to a target model using a set of transformation rules. Finally, the validation is supported by OO jDREW to evaluate the correctness and the adequacy of the model. This paper will apply an example of a virtual team to validate the feasibility of the RST/POSL framework.