Bayesian Topic Models
Bayesian Topic Models is a class of probabilistic generative models for discovering latent thematic structures in document collections through Bayesian inference over discrete topic assignments, distinguished by their joint modeling of documents as mixtures of topics and words as draws from topic-specific word distributions, with priors imposed on the latent variables to support principled uncertainty quantification and sparse, interpretable topic representations.
183
Publications
17K
Citations
498
Authors
214
Institutions
Publications per year
2017–2026
58
183
1–5 of 183
498
9
h-index
8
h-index
6
h-index
5
h-index
4
h-index
1–5 of 498
214
Massachusetts Institute of Technology
Cambridge, United States
9 h-index
26 publications
16.6K citations
Columbia University
New York, United States
8 h-index
11 publications
520 citations
Princeton University
Princeton, United States
7 h-index
12 publications
1.2K citations
Duke University
Durham, United States
7 h-index
22 publications
760 citations
Tsinghua University
Beijing, China
7 h-index
15 publications
731 citations
University of Illinois Urbana-Champaign
Urbana, United States
6 h-index
11 publications
1.2K citations
The University of Texas at Austin
Austin, United States
6 h-index
9 publications
544 citations

Hong Kong University of Science and Technology
Hong Kong, Hong Kong
6 h-index
9 publications
817 citations
1–8 of 214
Repository · 21 publications · 949 citations
16
h-index
Conference · 7 publications · 269 citations
7
h-index
TPAMI · 5 publications · 716 citations
5
h-index
Conference · 3 publications · 992 citations
3
h-index
TKDD · 3 publications · 62 citations
3
h-index
1–5