Complex Interactions in Social and Event Network Analysis

Modern social network analytic techniques, such as centrality analysis, outlier detection, and/or segmentation, are limited in that they typically only identify interactions within the dataset occurring as a first-order effect. In our previous work, we illustrated how the use of tensor decomposition can be used to identify multi-way interactions in both sparse and dense data-sets. The primary aim of this paper will be to introduce innovative extensions to our tensor decomposition approach that target and/or identify second and third order effects.

[1]  Jitendra Malik,et al.  Normalized Cuts and Image Segmentation , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Ian Davidson,et al.  Behavioral event data and their analysis , 2012, Data Mining and Knowledge Discovery.

[3]  Andrew B. Kahng,et al.  New spectral methods for ratio cut partitioning and clustering , 1991, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[4]  Mechthild Stoer,et al.  A simple min-cut algorithm , 1997, JACM.

[5]  Ian Davidson,et al.  Flexible constrained spectral clustering , 2010, KDD.

[6]  Ian Davidson,et al.  Active Spectral Clustering , 2010, 2010 IEEE International Conference on Data Mining.

[7]  Richard M. Leahy,et al.  An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Dorothea Wagner,et al.  Between Min Cut and Graph Bisection , 1993, MFCS.

[9]  Ian Davidson,et al.  Knowledge Driven Dimension Reduction for Clustering , 2009, IJCAI.

[10]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..