Social Network Analysis Based on Topic Model with Temporal Factor

Abstract

On social networks, each message has many features where the interested topics and the actors sending and receiving topics are important features. Unlike the traditional approach, which views each message belonging to a topic, the topic model is based on the approach, which indicates that each message has a mixture of many topics. However, topic model has limitations about discovering interested topics of actors with temporal factor and labelling latent topics. The article proposes a temporal-author-recipient-topic (TART) model based on: (i) discovering interested topics and analyzing the role of actors on social networks with the temporal factor; (ii) labelling the latent topics from topic model based on topic taxonomy; (iii) applying the temporal factor for finding the relation among factors in model; and (iv) finding out the variation of interested topics of actors with each period of time. An experimenting TART model on two corpora with 1,004,396 messages in Vietnamese and 25,009 actors by the software is built for SNA.