A Systematic Literature Review on English and Bangla Topic Modeling

Due to the enormous growth of information and technology, digitized texts data are being immensely generated. Therefore, identifying main topics in a vast collection documents by humans is merely impossible. Topic modeling such statistical framework that infers latent underlying from text documents, corpus, or electronic archives through probabilistic approach. It promising field Natural Language Processing (NLP). Though many researchers have researched this field, only few significant research has been done for Bangla. In literature review paper, we followed systematic approach reviewing topic studies published 2003 2020. We analyzed methods different aspects identified gap between English Bangla language. After analyzing these papers, several types techniques, as Latent Dirichlet Allocation (LDA), Semantic Analysis (LSA), Support Vector Machine (SVM), Bi-term Modeling (BTM). Furthermore, paper also highlights real-world applications modeling. Several evaluation were used evaluate models’ performances, which discussed study. conclude mentioning huge future scopes