Text Analysis of the Speech by Master Yulin Han

Abstract

By using the text analysis method commonly used in digital humanities researches, this paper explores the core ideas of I-Kuan-Tao Master Yulin Han with the corpus of 40 speeches delivered by him in 1980-1989 and 1990-1994 as the research material. The research team members first digitized the speech data by manual listening and typing, and the total number of words in all documents exceeded 255,000 words. We used the Python programming language to develop tools for extracting key words from the corpus based on the Jieba Chines word segmentation tool, then analyzed word frequency and built a database with Pandas. From the results of text analysis, we identified 20 core ideas of Master Yulin Han. Through rigorous digitization of the corpus, and the automated methods of Text mining and quantitative analysis, this paper explores the core ideas of Master Yulin Han from his speeches delivered to different audience at different periods. Using this methodology, we can investigate the ideological system of Master Yulin Han and how he constructs and interprets the morality of I-Kuan-Tao, which provides a more objective basis for the related research of his core ideas.

Keywords

• text analysis
• chinese word segmentation
• word frequency analysis
• master yulin han
• i-kuan-tao