SEMINAR

DEPARTMENT OF COMPUTER ENGINEERING

ABSTRACT

ON-LINE NEW EVENT DETECTION AND TRACKING IN A MULTI-RESOURCE ENVIRONMENT

Hakan Kurt

M.S. in Computer Engineering

Supervisor:

Prof. Dr. H.Altay Güvenir

As the amount of electronically available information sources increase, the need for information also increases. Today, it is almost impossible for a person to keep track all the information sources and find new events as soon as possible. In this thesis, we present an on-line new event detection and tracking system, which automatically detects new events from multiple news sources and immediately start tracking events as they evolve. Since we implemented on-line version of event detection approach, the decision about the news story is done before processing the next one. We also present a new threshold, called support threshold, used in detection process to decrease the number of new event alarms, which are caused by the false alarms, informative and one-time-only news. Support threshold can be used as priority or confidence weights of news sources. We implemented the tracking phase as an unsupervised learning process, that is detected events are automatically tracked by training the system using the first news story of an event. Since events evolve over time, an unsupervised adaptation is used to retrain the tracking system in

order to increase the tracking system performance. Adaptation is achieved by adding predicted events to the training process. From the corpus observations, we conclude that one news story can talk about more than one event. In order to approach the real-life properties of news, the tracking system is implemented as to relate a news story to more than one event. The on-line new event detection and tracking system has been tested on the Reuters news feed, available on Internet. The Reuters news feed that we used comprises four independent news sources and the news reports are in Turkish.

Keywords:Event detection, event tracking, information retrieval

The Seminar will be on 11 September 2001 at 10.30 in EA409