Extraction of Spatio-Temporal Data for Social Networks

It is often possible to better understand group change over time through examining social network data in a spatial and temporal context. Providing that context from a text analysis perspective requires identifying locations and associating them with people. This paper presents our GeoRef algorithm to automatically do this person-to-place mapping. It involves the identification of location, and uses syntactic proximity of words in the text to link location to person’s name. We describe an application using the algorithm based upon a small set of data from the Sudan Tribune divided into three periods in 2006 for the Darfur crisis. Contributions of this paper are (1) techniques to mine for location from text (2) techniques to mine for social network edges (associations between location and person), (3) use of the mined data to make spatio-temporal maps, and (4) use of the mined data to perform social network analysis.