Study on SNS graph generation and prediction

As the users of social network sites increases, the types of applications service social network sites provide are becoming more and more. This paper establishes an SNS graph generation model based on social services provided by kaixin.com, which describes the intrinsic relationship of entities (users, groups, applications, posts, and albums) in the site; extracts some rules according to the relationship of entities and applies these rules to the SNS graph generation, so the SNS graph can be updated dynamically with the selected social network site;Finally proposes an algorithm used to predict which applications may obtain more users in the future roughly based on SNS graph and according to the prediction results the social network site can adjust its website structure thereby absorbing more users.