Self-adaptive emergency topic tracking model based on CHI_LDA and timing characteristics

According to some flaws in the existing topic tracking methods, a new method of self-adaptive emergency topic tracking model based on CHI_LDA and timing characteristics is proposed in this paper. Apply the CHI_LDA method to establish the model for the news topics and reports, not only resolving the problems of high dimension and sparseness in the feature space and semantic relevance, but also improving the time efficiency for the LDA method to realize the semantic mapping of the feature space. Then establish the topic tracker combined with the news topic timing characteristics, and meanwhile realize the self-adaptive updating of the topic model so as to track the dynamic changes in topic. Experimental results indicate that this method of topic tracking has a better performance, further improving the effect of topic tracking.