Mapping World Events

Techniques are described which attempt to synthesise world events based on 15,000 news reports culled from the Internet each day, and to detect and visualise Breaking News Stories derived from changes in Flux and clustering analysis Statistical Indicators for individual countries have been defined, and software written which calculates these thematic indicators for all world countries. This work builds on the Europe Media Monitor (EMM) in use by the European Commission ( http://press.jrc.it ). EMM has invented a powerful method of rapidly classifying multilingual articles by matching weighted combinations of phrase and word patterns. The articles are cross-classified according to the countries mentioned and to general themes like "Conflict" "FoodSecurity" "Natural Disaster" "Ecology" and so on. The Alert system runs 24 hours per day keeping continuous hourly statistics on article populations. This allows SOTW to provide real-time graphical presentations of "news maps" time series of Indicators, and animations of crisis developments. More detailed geolocation of news based on Town names and Gazetteers, coupled with a "Top News" clustering algorithm results in 24 hourly News distributions. This technique also links clusters through to different language versions and back through time. Geospatial representation of news developments enables decision makers to better sumarise

BEST Clive;  VAN DER GOOT Erik;  BLACKLER Kenneth;  GARCIA DOMINGO Teofilo;  HORBY David;  STEINBERGER Ralf;  POULIQUEN Bruno; 

2006-10-16

Springer Verlag

JRC31089

https://publications.jrc.ec.europa.eu/repository/handle/JRC31089,