Title :
Improving the Performance of Topic Tracking System by Ensemble
Author :
Qin, Xiangju ; Zhang, Yang
Author_Institution :
Coll. of Inf. Eng., Northwest A&F Univ., Yangling
Abstract :
The aim of topic tracking is to monitor the stream of news stories to find additional stories on a topic that was identified by several sample stories. In this paper, we adopt majority voting to ensemble several topic tracking systems. The experiment results on TDT3 corpus show that our ensemble topic tracking system performs better than each individual topic tracking system, and that the performance of topic tracking system could be improved by ensemble technology.
Keywords :
pattern classification; text analysis; binary classification problem; ensemble technology; ensemble topic tracking system; majority voting; text classification; Classification algorithms; Computer science; Educational institutions; Information filtering; Information filters; Information retrieval; Monitoring; Performance evaluation; Software engineering; Voting; Ensemble; TDT3 Corpus; Topic Tracking;
Conference_Titel :
Computer Science and Software Engineering, 2008 International Conference on
Conference_Location :
Wuhan, Hubei
Print_ISBN :
978-0-7695-3336-0
DOI :
10.1109/CSSE.2008.984
