A novel text mining algorithm based on deep neural network

In this paper, we propose the novel text mining algorithm based on the deep neural network. In knowledge representation, capable of embodying the of the information content characteristic and external characteristic not only has the semantic meaning and it is interlinked, the content and the external characteristics constitute the text knowledge mining association reveals and knowledge base. This article through to the contents of a text knowledge characteristics and appearance characteristics of general different combination of co-occurrence analysis, explore the co-occurrence analysis method based on spatial distribution, time distribution and the application of the internal and the external association mapping text knowledge mining. In terms of the types of mining, not only limited to the simple knowledge classification, clustering, we found that can explore richer knowledge mining method, such as semantic rules found, trend analysis, topic tracking, etc. Under this prior basic knowledge, we propose the novel algorithm with the DNN. The experiment result proves the feasibility.