Research On Subject And Development Rule Of Statistics In China Based On Text Content Analysis

At present,the value of data has been generally recognized.As a subject of data research,statistics is widely used in various fields.However,with the advent of the era of big data,the characteristics of data have changed significantly,the amount of data has become larger,the types of data have become more,and the data structure has become more complex.The new characteristics of data have gone beyond the capability of traditional data management system and processing mode.In the face of this situation,statistics needs to be developed to cope with changes in data characteristics.Therefore,it is very important to reflect and review the past development of statistics.Understanding the development process of statistics can not only further understand the current situation of statistics,but also adjust the direction in time according to the background of the times,and explore a way of discipline development with the characteristics of the times.Therefore,from the perspective of literature research,this paper analyzes the research hotspot,research topic and development trend of "Statistics" published in the core and above journals of CNKI from 2000 to 2019 by using bibliometrics,text classification,atlas technology and other methods.First of all,the main information of the literature is analyzed by bibliometrics.The main body of the literature includes annual volume,cooperation,author,keyword frequency.Through analysis,this paper finds that the development of statistics can be divided into two stages: the stage of application development of Statistics(2000-2008)and the stage of development of Statistics(2008-2019).Secondly,cluster analysis of literature content information is selected.This paper focuses on the clustering analysis of literature keywords.The key words are the author's summary of the article,generally including research objects,research methods and other information,and has a certain degree of professionalism.By cluster analysis,we can get the research topic and the change of research topic.It is found that the subjects of statistical research can be divided into four categories: statistical method application,statistical quality test,spatial statistics,interdisciplinary application and statistical teaching.Thirdly,time exogenous labels are generated for all kinds of research topics,and the evolution rules and development status of each research topic are obtained.Through the analysis,we can see that the research themes of statistical method application and statistical quality test have a slight upward trend;the teaching research themes of spatial statistics and statistical discipline have a fast upward trend;the interdisciplinary application research themes have a downward trend.Finally,this paper summarizes and prospects the content of this paper,summarizes the research results in this paper,research deficiencies,and in the prospect of the follow-up research direction to explore.