On Developing Data Integration and Mining Platform for Classical Chinese Literature Study

With advancement of data digitization hardware and software, we have witnessed many successful applications of computer-aided methodologies in literature study and analysis. Recently, the data integration and mining technique became an important research topic, as it is a critical yet challenging issue in the development of effective digital platform to facilitate various practical literature research tasks, such as categorization of large literature data, identification of authors or interested readers from given texts, etc. In this paper, we study the processing of Chinese classic literature data, discuss a group of related data processing techniques, and then provide a few general suggestions in effectively applying these techniques.