Wavelet-Based Clustering of Social-Network Users Using Temporal and Activity Profiles
Encouraged by the success of social networking platforms, more and more enterprises are exploring the use of crowd-sourcing as a method for intra-organization knowledge management. There is not much information about their effectiveness though. While there has been some emphasis on studying friend networks, not much emphasis has been given towards understanding other kinds of user behavior like regularity of access or activity. In this paper we present a wavelet-based clustering method to cluster social-network users into different groups based on their temporal behavior and activity profiles. Cluster characterization reveals the underlying user-group characteristics. User data from web and enterprise social-network platforms have been analyzed.
KeywordsSocial Network Analysis Wavelet transformation Hierarchical K-means clustering
- 2.Acharya, S., Smith, B., Parnes, P.: Characterizing User Access to videos on the World Wide Web. In: Proceedings of MMCN (2000)Google Scholar
- 3.Xie, Y., Phoha, V.V.: Web user clustering from access log using belief function. In: Proceedings of the First International Conference on Knowledge Capture (K-CAP 2001), pp. 202–208. ACM Press, New York (2001)Google Scholar
- 4.Yang, J., Leskovec, J.: Patterns of Temporal variation in Online MediaGoogle Scholar
- 5.Graps, A.: An introduction to Wavelets. IEEE, Los Alamitos (1995)Google Scholar
- 6.Li, T., Li, Q., Zhu, S., Ogihara, M.: A Survey on wavelet Application in Data Mining. ACM SIGKDD Exploration Newsletter 4(2) (2002)Google Scholar