트우ㅣ트 분석기 인터페이스 

library(stringr)

library(rJava)

.jinit()

.jaddClassPath('C:/Program Files/R/R-3.6.1/library/KoNLP/java/korean-text-3.0.jar')

.jaddClassPath('C:/Program Files/R/R-3.6.1/library/KoNLP/java/scala-library-2.11.8.jar')

.jaddClassPath('C:/Program Files/R/R-3.6.1/library/KoNLP/java/twitter-text-1.11.1.jar')

twitterObj <- .jnew('com.twitter.penguin.korean.TwitterKoreanProcessorJava$Builder')

twitterObj <- .jrcall(twitterObj, 'build')

job <- read.csv("C:/data/kdn_jobplanet.csv")

st <- job$기업장점

st1 <- paste0(st,collapse="")

st2 <- as.data.frame(st)

# 트위트 형태소 함수 설정====================================

twi.extractNoun <- function(strings){

  res = .jrcall(twitterObj, 'tokenize', strings)

  res = .jstrVal(res)

  res = str_match_all(res, "([가-힣]+)\\(Noun")[[1]][,2]

  res= res[nchar(res)>=2]

  res

}

word1 <- apply(st2,1,twi.extractNoun)

twitter_sentence <- sapply(word1, function(x) { paste0(as.character(unlist(x)), collapse=" ") })