Evolving Social Networks Analysis via Tensor Decompositions: From Global Event Detection Towards Local Pattern Discovery and Specification
- 676 Downloads
Existing approaches for detecting anomalous events in time-evolving networks usually focus on detecting events involving the majority of the nodes, which affect the overall structure of the network. Since events involving just a small subset of nodes usually do not affect the overall structure of the network, they are more difficult to spot. In this context, tensor decomposition based methods usually beat other techniques in detecting global events, but fail at spotting localized event patterns. We tackle this problem by replacing the batch decomposition with a sliding window decomposition, which is further mined in an unsupervised way using statistical tools. Via experimental results in one synthetic and four real-world networks, we show the potential of the proposed method in the detection and specification of local events.
KeywordsTime-evolving social networks Tensor decomposition Event detection
This work is financed by National Funds through the Portuguese funding agency, FCT - Fundação para a Ciência e a Tecnologia within project: UID/EEA/50014/2019. Sofia Fernandes also acknowledges the support of FCT via the PhD grant PD/BD/114189/2016. The authors also acknowledge the SocioPatterns collaboration for making the dataset (in ) available.
- 2.Berlingerio, M., Koutra, D., Eliassi-Rad, T., Faloutsos, C.: Network similarity via multiple social theories. In: 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), pp. 1439–1440. IEEE (2013)Google Scholar
- 4.Costa, P.: Online Network Analysis of Stock Markets. Master’s thesis, University of Porto (2018)Google Scholar
- 5.Dawson, R.: How significant is a boxplot outlier? J. Stat. Educ. 19(2) (2011)Google Scholar
- 6.Desmier, E., Plantevit, M., Robardet, C., Boulicaut, J.-F.: Cohesive co-evolution patterns in dynamic attributed graphs. In: Ganascia, J.-G., Lenca, P., Petit, J.-M. (eds.) DS 2012. LNCS (LNAI), vol. 7569, pp. 110–124. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33492-4_11CrossRefGoogle Scholar
- 8.Isella, L., Stehlé, J., Barrat, A., Cattuto, C., Pinton, J.F., Van den Broeck, W.: What’s in a crowd? Analysis of face-to-face behavioral networks. J. Theor. Biol. 271(1), 166–180 (2011). http://www.sociopatterns.org/datasets/infectious-sociopatterns-dynamic-contact-networks/MathSciNetCrossRefGoogle Scholar
- 11.Koutra, D., Papalexakis, E.E., Faloutsos, C.: TensorSplat: spotting latent anomalies in time. In: Proceedings of the 2012 16th Panhellenic Conference on Informatics, PCI 2012, pp. 144–149. IEEE Computer Society (2012)Google Scholar
- 13.Papalexakis, E., Pelechrinis, K., Faloutsos, C.: Spotting misbehaviors in location-based social networks using tensors. In: Proceedings of the Companion Publication of the 23rd International Conference On World Wide Web Companion, pp. 551–552. International World Wide Web Conferences Steering Committee (2014)Google Scholar
- 16.Rayana, S., Akoglu, L.: An ensemble approach for event detection and characterization in dynamic graphs. In: ACM SIGKDD ODD Workshop (2014)Google Scholar
- 17.Rayana, S., Akoglu, L.: Less is more: building selective anomaly ensembles. ACM Trans. Knowl. Discov. Data (TKDD) 10(4), 42 (2016)Google Scholar