eCite Digital Repository

Change point detection for information diffusion tree


Ohara, K and Saito, K and Kimura, M and Motoda, H, Change point detection for information diffusion tree, Lecture Notes in Artificial Intelligence: Proceedings of the Discovery Science 18th International Conference (DS 2015), 4-6 October 2015, Banff, AB, Canada, pp. 161-169. ISBN 978-3-319-24281-1 (2015) [Refereed Conference Paper]

Not available

Copyright Statement

Copyright 2015 Springer International Publishing

Official URL: 14

DOI: doi:10.1007/978-3-319-24282-8_14


We propose a method of detecting the points at which the speed of information diffusion changed from an observed diffusion sequence data over a social network, explicitly taking the network structure into account. Thus, change in diffusion is both spatial and temporal. This is different from most of the existing change detection approaches in which all the diffusion information is projected on a single time line and the search is made in this time axis. We formulate this as a search problem of change points and their respective change rates under the framework of maximum log-likelihood embedded in MDL. Time complexity of the search is almost proportional to the number of observed data points and the method is very efficient. We tested this using both a real Twitter date (ground truth not known) and the synthetic data (ground truth known), and demonstrated that the proposed method can detect the change points efficiently and the results are very different from the existing sequence-based (time axis) approach (Kleinberg’s method).

Item Details

Item Type:Refereed Conference Paper
Keywords:social networks, information diffusion, change point detection
Research Division:Information and Computing Sciences
Research Group:Information systems
Research Field:Information security management
Objective Division:Expanding Knowledge
Objective Group:Expanding knowledge
Objective Field:Expanding knowledge in the information and computing sciences
UTAS Author:Motoda, H (Dr Hiroshi Motoda)
ID Code:109269
Year Published:2015
Deposited By:Information and Communication Technology
Deposited On:2016-06-06
Last Modified:2018-01-17

Repository Staff Only: item control page