Dynamic hyperparameter optimization for bayesian topical trend analysis

Tomonari Masada, Daiji Fukagawa, Atsuhiro Takasu, Tsuyoshi Hamada, Yuichiro Shibata, Kiyoshi Oguri
2009 Proceeding of the 18th ACM conference on Information and knowledge management - CIKM '09  
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
more » ... ng and evaluate our proposal by link detection task of Topic Detection and Tracking.
doi:10.1145/1645953.1646242 dblp:conf/cikm/MasadaFTHSO09 fatcat:4zgmx3vfg5h5xe2xjokir5gdaq