The discovery of user related rare sequential patterns of topics in the internet document stream

On the Internet, plain text documents created and viewed by users constitute ever changing document streams. Lots of the literature is devoted to topic modeling, while the sequential patterns of topics in document streams are ignored. In this paper, we deal with the problem of mining user related rare sequential patterns of topics in the Internet document streams, which can be used in many fields, such as real-time user behavioral monitoring on the Internet. We propose an approach to discover rare patterns based on the temporal and probabilistic information of topics. Experiments show that the proposed approach can discover user related rare patterns of topic effectively.