We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions...
William Yang Wang, Elijah Mayfield, Suresh Naidu, ...
One of the major strengths of probabilistic topic modeling is the ability to reveal hidden relations via the analysis of co-occurrence patterns on dyadic observations, such as docu...
Abstract. The Aviation Safety Reporting System (ASRS) is used to collect voluntarily submitted aviation safety reports from pilots, controllers and others. As such it is particular...
Probabilistic Latent Semantic Analysis (PLSA) has become a popular topic model for image clustering. However, the traditional PLSA method considers each image (document) independen...
Social media such as Web forum often have dense interactions between user and content where network models are often appropriate for analysis. Joint non-negative matrix factorizat...