Using contextual analysis for news event detection

The rapidly growing amount of newswire stories stored in electronic devices raises new challenges for information retrieval technology. Traditional qu ery-driven retrieval is not suitable for generic queries. It is desirable t o have an intelligent system to automatically locate topically related even ts or topics in a continuous stream of newswire stories. This is the goal o f automatic event detection. We propose a new approach to performing event detection from multilingual newswire stories, Unlike traditional methods wh ich employ simple keyword matching, our method makes use of concept terms a nd named entities such as person, location, and organization names. Concept terms of a story are derived from statistical context analysis between sen tences in the news story and stories in the concept database. We have condu cted a set of experiments to study the effectiveness of our approach. The r esults show that the performance of detection using concept terms together with story keywords is better than traditional methods which only use keywo rd representation. (C) 2001 John Wiley & Sons, Inc.