Implementation of Burmese Language News Classification System by Using SVM and LSTM Machine Learning Algorithm

With the increasing availability of documents in social media and the rapid growth in the number of data exchange systems, the task of automatically categorizing documents has become a key method for organizing information and knowledge retrieval. News classification is the process of sorting text documents into one or more predefined categories or classes of similar documents. The correct classification of electronic documents, online News, blogs, electronic letters and digital libraries requires intellectual analysis of the text, the use of machine learning and methods of a natural language processing to obtain significant information. The article aims to analyze the methods and methodologies that are used in the classification of text documents. The purpose of the work is to classify news in social media that need to be organized and retrieved information using machine learning methods. In this paper, Experiments were done on Myanmar local and international news dataset using TF-IDF feature extraction techniques and the results are compared with performance of Support Vector Machine (SVM) machine learning algorithm and long short-term memory (LSTM) recurrent neural network.