@inproceedings{f967b8d9fcd943179d856e2a7bd32e72,
title = "Automatic topic detection with an incremental clustering algorithm",
abstract = "At present, most of the topic detection approaches are not accurate and efficient enough. In this paper, we proposed a new topic detection method (TPIC) based on an incremental clustering algorithm. It employs a self-refinement process of discriminative feature identification and a term reweighting algorithm to accurately cluster the given documents which discuss the same topic. To be efficient, the {"}aging{"} nature of topics is used to precluster stories. To automatically detect the true number of topics, Bayesian Information Criterion (BIC) is used to estimate the true number of topics. Experimental results on Linguistic Data Consortium (LDC) datasets TDT4 show that the proposed method can improve both the efficiency and accuracy, compared to other methods.",
keywords = "Incremental clustering, TDT, Term reweighting, Topic Detection",
author = "Xiaoming Zhang and Zhoujun Li",
year = "2010",
doi = "10.1007/978-3-642-16515-3\_43",
language = "英语",
isbn = "3642165141",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
number = "M4D",
pages = "344--351",
booktitle = "Web Information Systems and Mining - International Conference, WISM 2010, Proceedings",
edition = "M4D",
note = "2010 International Conference on Web Information Systems and Mining, WISM 2010 ; Conference date: 23-10-2010 Through 24-10-2010",
}