Evaluation of a System Utilizing User Interaction to Track Interesting News Events
平田紀史, 白松俊, 大囿忠親, 新谷虎松


An experiment is conducted to evaluate the usability of a system we have proposed to track events related to news articles on the Web. The system's user interface helps users obtain a better understanding of the content and background of news articles. Its user input-system output interaction enables users' interests to be taken into consideration in structuring related events, which is necessary for helping users to understand the events better. The system presents related events in the form of graph structures called ``event graphs''. Event graphs based on users' interests are produced by iterating over event presentation and user selection. The system also reduces processing time by restricting the range of words used in processing users' input. Experimental results using actual news articles show that the system effectively extracts useful events for understanding the articles.