Abstract
Analyzing topic evolution is an effective way to monitor the overview of topic spreading. Existing methods have focused either on the intensity evolution of topics along a timeline or the topic evolution path of technical literature. In this paper, we aim to study topic evolution from a micro perspective, which not only captures the topic timeline but also reveals the topic status and the directed evolutionary path among topics. Firstly, we construct a word network by co-occurrence relationship between feature words. Secondly, Latent Dirichlet allocation (LDA) model is used to automatically extract topics and capture the mapping relationship between words and topics, and then a 'word-topic' coupling network is built. Thirdly, based on the 'word-topic' coupling network, we describe the topic intensity evolution over time and measure topic status considering the contribution of feature words to a topic. The concept of topic drifting probability is proposed to identify the evolutionary path. Experimental results conducted on two real-world data sets of "COVID-19" demonstrate the effectiveness of our proposed method.