This is a data analysis code in R language, the purpose is to calculate the network structure of URLs under different Discipline\PY\Tweet. When visualising the data, the histogram distribution under different disciplines, years, and tweets based on author and non-author in two groups Because the tweet column is a numeric column, I classify tweets in the top 10% as high tweets, top10%-top50%, medium tweets, and low tweets in the top 50% or less. The tweet columns are divided into three groups, the subject column is 10 groups and the year column is 5 groups, comparing the differences between groups in different tweets\subjects and years~