2009
Dynamic hyperparameter optimization for bayesian topical trend analysis
International Conference on Information and Knowledge Management, Proceedings
- ,
- ,
- ,
- ,
- ,
- First page
- 1831
- Last page
- 1834
- Language
- Publishing type
- Research paper (international conference proceedings)
- DOI
- 10.1145/1645953.1646242
- Publisher
- ACM
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. Copyright 2009 ACM.
- Link information
-
- DOI
- https://doi.org/10.1145/1645953.1646242
- DBLP
- https://dblp.uni-trier.de/rec/conf/cikm/MasadaFTHSO09
- Scopus
- https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=74549123327&origin=inward
- Scopus Citedby
- https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=74549123327&origin=inward
- URL
- http://doi.acm.org/10.1145/1645953.1646242
- URL
- http://dblp.uni-trier.de/db/conf/cikm/cikm2009.html#conf/cikm/MasadaFTHSO09
- ID information
-
- DOI : 10.1145/1645953.1646242
- DBLP ID : conf/cikm/MasadaFTHSO09
- SCOPUS ID : 74549123327