A SURVEY ON VIETNAMESE TEXT CLASSIFICATION MODELS

Abstract

Text classification is one of the basic tasks of Natural Language Processing, widely applied in sentiment analysis, spam detection, topic labeling, intent detection, etc. The explosion of information sources on the Web, social networks... makes it more and more important and attracts many researchers. Many feature selection methods and classification algorithms have been proposed to use. However, the rapid increase of big data is creating challenges for text classification in general and Vietnamese language in particular, such as the problem of application expansion, the ability to classify social problems, etc. The purpose of this report is to examine the research on text classification including Vietnamese, in order to provide readers with an overview of existing text classification technologies and topics. propose ways to solve challenging problems in text classification.