Inproceedings,
Mining the web to predict future events
WSDM, page 255-264. ACM, (2013)
DOI: 10.1145/2433396.2433431
Abstract
We describe and evaluate methods for learning to forecast
forthcoming events of interest from a corpus containing 22
years of news stories. We consider the examples of identi-
fying signi cant increases in the likelihood of disease out-
breaks, deaths, and riots in advance of the occurrence of
these events in the world. We provide details of methods
and studies, including the automated extraction and gener-
alization of sequences of events from news corpora and mul-
tiple web resources. We evaluate the predictive power of the
approach on real-world events withheld from the system.
