Research in crisis management is a relatively new area of study, originating in the 1980s. Researchers have created several different models that separate organizational crises into discrete stages, such as pre-crisis, crisis and post-crisis. In this article, we discuss a natural language based crisis detection system which classifies news articles relating to crises into the appropriate crisis stage. We use news articles from the New York Times as a source of training data, and use this data along with state of the art data mining and machine learning algorithms as the core of the system. In the future, our system may be expanded to identify and evaluate crisis management strategies, suggest crisis management strategies for the current state of a crisis, or provide stakeholders with summaries of crises in news media.
|Title of host publication||Innovations in News Media: Crisis Classification System|
|Publisher||Industrial Conference on Data Mining|
|State||Published - 2016|