An integrated model for discovering, classifying and labeling topics based on topic modeling

Abstract

In this paper, we propose an integrated model for discovering, classifying and labeling topics of messages based on topic modeling to analyze and understand the topics of the messages posted by users on social networks. In which, the method of labeling is executed by machine learning on the training data and ontology. The ontology is created in the field of higher education. All parts of model are integrated on a system called social network analysis system based on topic modeling. The experiment of the model on the linguistic data of Vietnamese texts collected from a student forum is transformed into a data structure of social network, including: 13,208 messages by 2,494 users.