Spatiotemporal Network Analysis and Visualization
Judith Gelernter and
Kathleen M. Carley
Additional contact information
Judith Gelernter: Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA
Kathleen M. Carley: Institute for Software Research, Carnegie Mellon University, Pittsburgh, PA, USA
International Journal of Applied Geospatial Research (IJAGR), 2015, vol. 6, issue 2, 77-97
Abstract:
Spatiotemporal social network analysis shows relationships among people at a particular time and location. This paper presents an algorithm that mines text for person and location words and creates connections among words. It shows how this algorithm output, when chunked by time intervals, may be visualized by third-party social network analysis software in the form of standard network pin diagrams or geographic maps. Its data sample comes from newspaper articles concerning the 2006 Darfur crisis in Sudan. Given an immense data sample, it would be possible to use the algorithm to detect trends that would predict the next geographic center(s) of influence and types of actors (foreign dignitaries or domestic leaders, for example). This algorithm should be widely generalizable to many text domains as long as the external resources are modified accordingly.
Date: 2015
References: Add references at CitEc
Citations: View citations in EconPapers (1)
Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/ijagr.2015040105 (application/pdf)
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:igg:jagr00:v:6:y:2015:i:2:p:77-97
Access Statistics for this article
International Journal of Applied Geospatial Research (IJAGR) is currently edited by Donald Patrick Albert
More articles in International Journal of Applied Geospatial Research (IJAGR) from IGI Global
Bibliographic data for series maintained by Journal Editor ().