Abstract:
Digital text is increasing rapidly on the Internet with the excessive use of social media. For this reason, it is very challenging to extract effective information from t...View moreMetadata
Abstract:
Digital text is increasing rapidly on the Internet with the excessive use of social media. For this reason, it is very challenging to extract effective information from the digital text due its high dimensionality, sparseness and big data. In this paper, we study the powerful nonparametric Bayesian topic model which is Hierarchical Latent Dirichlet Allocation (hLDA). We deal the issue of learning topics hierarchies from Urdu text data. The presented Topic Model for Urdu is combined with preprocessing activities, hLDA model, and Gibbs Sampling (GS) algorithm. We present hLDA base topic model called Urdu Hierarchical Latent Dirichlet Allocation (uhLDA). Empirical study showed that uhLDA effectively learns the topics hierarchies from 5000 Urdu text documents. Furthermore, we evaluated the results using Pointwise Mutual information (PMI) and it shows that uhLDA outperforms as compared to existing standard topic model LDA.
Date of Conference: 05-07 September 2019
Date Added to IEEE Xplore: 11 November 2019
ISBN Information: