关键词: 社交网络, 用户发现, 忠诚度, RFM, 社区划分

Abstract: Aiming at improving the users’ high viscosity in the social network, a discoveried algorithm based on loyalty in social network system was proposed. The proposed algorithm used double Recency Frequency Monetary (RFM) model for mining the different loyalty kinds of users. Firstly, according to the double RFM model, the users’ consumption value and behavior value was calculated dynamically and the loyalty in a certain time was got. Secondly, the typical loyal users and disloyal users were found out by using the founded standard curve and the similarity calculation. Lastly, the potential loyal and not loyal users were found out by using the modularity-based community discovery and independent cascade propagation model. On some microblog datasets of a social network, the quantitative representation of user loyalty were confirmed. Thus the users were can be distinguished based on users’ loyalty. The experimental results show that the proposed algorithm can effectively dig out different loyalty kinds of users, and can apply to personalization recommendation or marketing, etc.in the social network system.

Key words: social networking services, user discovery, loyalty, RFM, community discovery