DSpace university logo mark
Advanced Search
Japanese | English 

NAOSITE : Nagasaki University's Academic Output SITE > Faculty of Engineering > Conference Paper >

Modeling topical trends over continuous time with priors

File Description SizeFormat
LNCS6064_302.pdf314.57 kBAdobe PDFView/Open

Title: Modeling topical trends over continuous time with priors
Authors: Masada, Tomonari / Fukagawa, Daiji / Takasu, Atsuhiro / Shibata, Yuichiro / Oguri, Kiyoshi
Issue Date: 2010
Publisher: Springer
Citation: Lecture Notes in Computer Science, 6064(2), pp.302-311; 2010
Abstract: In this paper, we propose a new method for topical trend analysis. We model topical trends by per-topic Beta distributions as in Topics over Time (TOT), proposed as an extension of latent Dirichlet allocation (LDA). However, TOT is likely to overfit to timestamp data in extracting latent topics. Therefore, we apply prior distributions to Beta distributions in TOT. Since Beta distribution has no conjugate prior, we devise a trick, where we set one among the two parameters of each per-topic Beta distribution to one based on a Bernoulli trial and apply Gamma distribution as a conjugate prior. Consequently, we can marginalize out the parameters of Beta distributions and thus treat timestamp data in a Bayesian fashion. In the evaluation experiment, we compare our method with LDA and TOT in link detection task on TDT4 dataset. We use word predictive probabilities as term weights and estimate document similarities by using those weights in a TFIDF-like scheme. The results show that our method achieves a moderate fitting to timestamp data.
Description: Advances in Neural Networks - ISNN 2010 : 7th International Symposium on Neural Networks, ISNN 2010, Shanghai, China, June 6-9, 2010, Proceedings, Part II / The original publication is available at www.springerlink.com
URI: http://hdl.handle.net/10069/23580
ISBN: 3642133177 / 978-364213317-6
ISSN: 03029743
DOI: 10.1007/978-3-642-13318-3_38
Rights: © 2010 Springer-Verlag.
Type: Conference Paper
Text Version: author
Appears in Collections:Conference Paper

Citable URI : http://hdl.handle.net/10069/23580

All items in NAOSITE are protected by copyright, with all rights reserved.


Valid XHTML 1.0! Copyright © 2006-2015 Nagasaki University Library - Feedback Powerd by DSpace