| Based on the data from 2017 to 2019,this paper studies the factors influencing the output of high-quality articles by top scholars in the field of computer science at home and abroad in the past three years,and compares the differences at home and abroad.Firstly,a descriptive statistical analysis was made from the perspectives of the number of highquality articles produced by scholars in the past three years,gender,age and academic research status of scholars,including theoretical research strength,theoretical application ability,influence of attending conferences and influence of collaborators,etc.,revealing the differences between top scholars in the field of computer science at home and abroad.Secondly,based on two sets of domestic and foreign data,Poisson regression and negative binomial regression models are respectively used to study the influencing factors of the output quantity of high-quality articles in the recent three years.Considering that in the sample data,there are a large number of zeros in the observed values of the output quantity of highquality articles by scholars in the recent three years,in order to better mine the information contained in zeros,the zero-inflated counting model is used in this paper.It is found that the zero-inflated Poisson regression model has a good fitting effect for foreign scholars' data.For domestic scholars,the zero-inflated negative binomial regression model has a good fitting effect.Finally,through the comparative analysis of the modeling results of two sets of data at home and abroad,we find that: no matter at home or abroad,the number of high-quality papers issued by scholars in the field of computer science often has a greater relationship with the influence of collaborators;In the field of computer science,age and theoretical application ability of foreign scholars are very important factor affecting the publication of articles,while gender is a very important factor in China. |
PDF Full Text Request