AN ALGORITHM TO INFER SPATIOTEMPORAL DIFFUSION NETWORKS
Open Access
- Author:
- Xu, Fangcao
- Graduate Program:
- Geography
- Degree:
- Master of Science
- Document Type:
- Master Thesis
- Date of Defense:
- December 07, 2018
- Committee Members:
- Donna Peuquet, Thesis Advisor/Co-Advisor
Bruce Desmarais, Committee Member
Guido Cervone, Committee Member - Keywords:
- Spatiotemporal diffusion; Network Inference; Survival analysis
- Abstract:
- Information, ideas, and diseases, or more generally, contagions, spread over space and time through individual transmissions via our social networks, as well as through external sources. A detailed picture of any diffusion process can be achieved only when both a good network structure and diffusion cascades are obtained. The advent of rich social, media and locational data (e.g., Tweets, RSS news feeds, and GPS), allows us to study and model this diffusion process in more detail than previously possible. Nevertheless, how information, ideas or diseases are propagated through the network are difficult to trace. This propagation is continuous over space and time, where individual transmissions occur at different rates via complex, latent connections. To tackle this challenge, a survival analysis model, using a proportional hazard function is developed in this research that uses both time and spatial distance as explanatory variables to simulate the diffusion process as well as an enhanced greedy algorithm built upon the NETINF algorithm to infer the network structure. The aim is to provide a more detailed measure of how different contagions are transmitted through the underlying spatiotemporal network at a large scale. Demonstration of the effectiveness and accuracy of the greedy algorithm will utilize a synthetic dataset and two different network structures, where nodes are geographic places with calculated infection time when contagions spread over edges.