A Performance Evaluation of Correlated and Dynamic Topic Modeling on a QA Dataset
K. R. Bindu, G.H. Gowrikrishna, Latha Parameswaran · 2019 3rd International conference on Electronics, Communication and Aerospace Technology (ICECA) · 2019
Topic modeling is a set of algorithms which is used to mine the data that is hidden inside a large collection of documents. In this paper we discusses about the Correlated topic modeling and dynamic topic modeling in detail and comparing their performance on a question answer dataset based on autism. Log Likelihood and Perplexity are the measures used for comparing the discussed topic modeling algorithms.