Wei Li, Xuerui Wang, Andrew McCallum
Recent work in statistical topic models has investigated richer structures to capture either temporal or inter-topic correlations. This paper introduces a topic model that combines the advantages of two recently proposed models: (1) The Pachinko Allocation model (PAM), which captures arbitrary topic correlations with a directed acyclic graph (DAG), and (2) the Topics over Time model (TOT), which captures time-localized shifts in topic prevalence with a continuous distribution over timestamps. Our model can thus capture not only temporal patterns in individual topics, but also the temporal patterns in their co-occurrences. We present results on a research paper corpus, showing interesting correlations among topics and their changes over time.
Subjects: 13. Natural Language Processing; 12. Machine Learning and Discovery
Submitted: May 17, 2006