Rating news documents for similarity

Electronic news has long held the promise of personalized and dynamic delivery of current event news items, particularly for web users. Although electronic versions of print news are now widely available, the personalization of that delivery has not yet been accomplished. In this paper, we present a methodology of associating news documents based on the extraction of feature phrases, where feature phrases identify dates, locations, people, and organizations. A news representation is created from these feature phrases to define news objects that can then be compared and ranked to find related news items. Unlike traditional information retrieval, we are much more interested in precision than recall. That is, the user would like to see one or more specifically related articles, rather than all somewhat related articles. The algorithm is designed to work interactively with the user using regular web browsers as the interface.