Research on the psychology of historical figures based on big data analysis and data mining : Taking Zeng Guofan's diary as an example

In recent years, big data analysis and data mining technologies play an irreplaceable role in all walks of life. In the general psychological research of historical figures, there are often the tendencies of pragmatism, subjectivism, absolutism, simplification and formulaic. Reasons for these phenomena are the lack of confirmation research of quantitative analysis. The application of big data analysis and data mining technology can analyze and mine the left real historical data. After using the big data analysis, we can scientifically summarize and discover the hidden laws. Therefore, we select the complete works of Zeng Guofan(Revised Version) as the original data. These articles are the most psychological representative in all Zeng Guofan’s articles. Then we use LIWC Ancient Chinese Dictionary and CC- LIWC analysis 3.6 system as the tools of big data analysis to quantify the psychological significance of natural language. We also deeply discuss the changes of specific keywords in Zeng Guofan's diary, and objectively restore the real psychological changes of Zeng Guofan in the two important historical periods. This study expands the application of big data analysis and mining, and provides scientific data support for the research of the psychology of historical figures.