Probabilistic Latent Semantic Analysis


  • A variant of Latent Semantic Analysis based on conditional Probability rather than on correlation. 1
  • A statistical procedure for finding the underlying dimensions of correlated terms. Like Latent Semantic Analysis, this procedure attempts to capture the meaning shared by multiple terms to provide a concept search capability. It differs some from LSA in that it involves a different statistical model. Also called probabilistic latent semantic indexing. 2


  1. Maura R. Grossman and Gordon V. Cormack, EDRM page & The Grossman-Cormack Glossary of Technology-Assisted Review, with Foreword by John M. Facciola, U.S. Magistrate Judge2013 Fed. Cts. L. Rev. 7 (January 2013).
  2. Herb Roitblat, Predictive Coding Glossary.