Optima Network Science Seminar
Faculty Advisor: My T. Thai
Coordinator: Thang N. Dinh
Time and place: 1:50pm Wed, E520A CSE Building
Note:
If you are
interested in participating in the activities of the seminar and/or wish to
receive emails about
upcoming events please send an email to tdinh@cise.ufl.edu.
by Soham Das on Jan 16, 2013
The recent explosion in the adoption of search engines and new media such as blogs and Twitter have facilitated faster propagation of news and rumors. How quickly does a piece of news spread over these media? How does its popularity diminish over time? Does the rising and falling pattern follow a simple universal law? In this paper, we propose SpikeM, a concise yet flexible analytical model for the rise and fall patterns of influence propagation. Our model has the following advantages: (a) unification power: it generalizes and explains earlier theoretical models and empirical observations; (b) practicality: it matches the observed behavior of diverse sets of real data; (c) parsimony: it requires only a handful of parameters; and (d) usefulness: it enables further analytics tasks such as forecasting, spotting anomalies, and interpretation by reverse engineering the system parameters of interest (e.g. quality of news, count of interested bloggers, etc.). Using SpikeM, we analyzed 7.2GB of real data, most of which were collected from the public domain. We have shown that our SpikeM model accurately and succinctly describes all the patterns of the rise-and-fall spikes in these real datasets.
Rise and Fall Patterns of Information Diffusion: Model and Implications
Yasuko Matsubara, Yasushi Sakurai, B. Aditya Prakash, Lei Li, Christos Falouts, in Proceedings of ACM SIGKDD 2012 [PDF][Slide]
AbstractThe recent explosion in the adoption of search engines and new media such as blogs and Twitter have facilitated faster propagation of news and rumors. How quickly does a piece of news spread over these media? How does its popularity diminish over time? Does the rising and falling pattern follow a simple universal law? In this paper, we propose SpikeM, a concise yet flexible analytical model for the rise and fall patterns of influence propagation. Our model has the following advantages: (a) unification power: it generalizes and explains earlier theoretical models and empirical observations; (b) practicality: it matches the observed behavior of diverse sets of real data; (c) parsimony: it requires only a handful of parameters; and (d) usefulness: it enables further analytics tasks such as forecasting, spotting anomalies, and interpretation by reverse engineering the system parameters of interest (e.g. quality of news, count of interested bloggers, etc.). Using SpikeM, we analyzed 7.2GB of real data, most of which were collected from the public domain. We have shown that our SpikeM model accurately and succinctly describes all the patterns of the rise-and-fall spikes in these real datasets.