在R中按频率排列文档术语矩阵中的单词

library(tm)
library(slam)

docs <- Corpus(VectorSource(c("文档1内容", "文档2内容", "文档3内容")))

docs <- tm_map(docs, content_transformer(tolower))
docs <- tm_map(docs, removePunctuation)
docs <- tm_map(docs, removeNumbers)
docs <- tm_map(docs, removeWords, stopwords("english"))
docs <- tm_map(docs, stripWhitespace)

dtm <- DocumentTermMatrix(docs)

term_freq <- row_sums(as.matrix(dtm))

sorted_terms <- sort(term_freq, decreasing = TRUE)

N <- 10
top_terms <- head(sorted_terms, N)
print(top_terms)