Abstract | ||
---|---|---|
Topic models are important tools for mining the potential topics of text. However, the existing topic model is mostly derived from latent Dirichlet allocation (LDA), which requires the number of topics to be specified in advance. In order to mine the topic of Chines micro-blogs automatically, we propose a nonparametric Bayesian model, named HDP-TUB model, which is derived from hierarchical Dirichlet Process (HDP). In this model, we assume non-exchangeability of data, and use temporal information, user information and theme tags (TUB) to solve the sparsity problem caused by the short text. In order to construct the HDP-TUB model, the CRF (Chinese Restaurant Franchise) method is extended to integrate the temporal information, user information and topic tag information. Experiments show that the HDP-TUB model outperforms the LDA model and the HDP model in the perplexity and the difference between topics. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/978-3-319-73618-1_75 | Lecture Notes in Artificial Intelligence |
Keywords | DocType | Volume |
Topic mining,HDP-TUB model,Hierarchical Dirichlet Process,Chinese Restaurant Franchise | Conference | 10619 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yaorong Zhang | 1 | 0 | 0.34 |
Bo Yang | 2 | 194 | 53.08 |
Yi Li | 3 | 3 | 3.87 |
Yi Liu | 4 | 131 | 54.73 |
Yangsen Zhang | 5 | 11 | 12.10 |