This paper presents a new Bayesian topical trend analysis. We regard the parameters of topic Dirichlet priors in latent Dirichlet allocation as a function of document timestamps and optimize the parameters by a gradient-based algorithm. Since our method gives similar hyperparameters to the documents having similar timestamps, topic assignment in collapsed Gibbs sampling is affected by timestamp similarities. We compute TFIDF-based document similarities by using a result of collapsed Gibbs sampling and evaluate our proposal by link detection task of Topic Detection and Tracking.
内容記述
Proceeding of the 18th ACM conference : Hong Kong, China, 2009.11.02-2009.11.06
雑誌名
Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09
ページ
1831 - 1834
発行年
2009
ISBN
978-160558512-3
DOI
10.1145/1645953.1646242
権利
c ACM 2009. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09. http://doi.acm.org/10.1145/1645953.1646242
著者版フラグ
author
出版者
ACM Press
引用
Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09, pp1831-1834; 2009
Dynamic hyperparameter optimization for bayesian topical trend analysis
ICIKMP2009_1831.pdf
(722.78KB)
NAOSITEについて