Topology and Semantic based Topic Dependency Structure Discovery

Abstract

As a key enabler in achieving the full potential of text data analysis, topic relationship dependency structure discovery is employed to effectively support the advanced text data analysis intelligent application. The proposed framework combines a complex network analysis approach and the Latent Dirichlet Allocation (LDA) model for topic relationship network discovery. The approach is to identify topics of the text data based on the LDA and to discover the graph structure of the inherent semantic association dependency among topics. This not only leverages a set of high-level topics covered by the text data but also exploits the semantic association relationship between them. The experimental results and analysis show that the proposed approach is efficient, feasible and practical. The results of the presented work imply that the topics and relationships between them can be discovered by this approach. And it also provides complete semantic interpretation.