An Event Detection Algorithm Based on Improved STC

In order to overcome some shortcomings of traditional algorithms in event detection, we propose an event detection algorithm based on improved STC (suffix tree clustering), which detects significant events from large volumes of news and presents the main content of the events to the user as summarie...

Full description

Saved in:
Bibliographic Details
Main Authors: Li-Qing Qiu, Bin-Pang, Li-Ping Zhao
Format: Conference Proceeding
Language:English
Subjects:
Clustering algorithms
Density functional theory
Distance measurement
Event detection
Merging
Mice
Text mining
Unsupervised learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to overcome some shortcomings of traditional algorithms in event detection, we propose an event detection algorithm based on improved STC (suffix tree clustering), which detects significant events from large volumes of news and presents the main content of the events to the user as summaries. The experimental results on TDT indicate that the new algorithm is an effective document clustering algorithm.
DOI:10.1109/ICNSC.2008.4525274