Development of Topic Modeling Framework Using Probabilistic Recurrent Neural Network
P. Lakshmi Prasanna · International Journal of Advanced Trends in Computer Science and Engineering · 2019
A topic model is a probability based model that finds the collection of documents.The basic concept is to treat the documents as combinations of topics in the topic model, and each topic is viewed as a probability distribution of the.In this paper we proposed LDA Algorithm using Probabilistic recurrent neural network (PRORNN) to classify the text documents.Topic modeling refers to the task of Discovering Latent Topics in the text corpus set, where the output is commonly represented as top terms appearing in each topic.This algorithm , probabilistic recurrent neural network (PRORNN) is implemented first with 2 News groups data set and later with 20 News groups dataset and all the results are tabulated.The performance of PRORNN algorithm was compared with the state of art of algorithms for topic classification.