On-line event detection from web news stream
Yan Fu, Mingquan Zhou, Xuesong Wang, Hua Luan · 2010
In order to improve detection efficiency of on-line web news stream, we propose a new method to accomplish detection task with window-adding, named entity recognition and suffix tree clustering. In our method, we make full use of informative elements of news stream(such as date, place, person and so on) to help detection process, and this method decreases text similarity computation greatly. Experimental results show that our method improves on-line event detection performance, without sacrificing detection precision.