A Cluster-based Approach for Automatic Social Network Construction

摘要

Social network is a relational connection between people and society; for instance, friendship, colleague, or any information exchange relationship. The most significant problem of a social network is the role of key persons, who convey important messages to all individuals. However, the most appropriate representatives are difficult to discover. Hence, this research aims to propose a method to pre-construct a social network automatically before interaction and pre-identify representatives inside the network. The research goals of this research are: (1) automatically construct a social network based on SOM and SNA, (2) verify the difference between pre-constructed and real social networks, and (3) identify key representatives and validate the efficiency of the social network.