作者: Tomonari Masada , Atsuhiro Takasu
DOI: 10.1007/978-3-319-08010-9_51
关键词:
摘要: This paper provides an application of sparse additive generative models (SAGE) for temporal topic analysis. In our model, called ChronoSAGE, modeling results are diversified chronologically by using document timestamps. That is, word tokens generated not only in a topic-specific manner, but also time-specific manner. We firstly compare ChronoSAGE with latent Dirichlet allocation (LDA) terms pointwise mutual information to show its practical effectiveness. secondly give example time-differentiated topics, obtained as lists, usefulness trend detection.