Differences

This shows you the differences between two versions of the page.

--- text_mining_example_with_korean_songs [2017/11/13 15:49] – [Twitter] hkimscil
+++ text_mining_example_with_korean_songs [2017/12/14 10:12] (current) – [Twitter] hkimscil
@@ Line 9: / Line 9: @@
 library(wordcloud)
 library(XLConnect)
+library(twitteR)
 # set your data dir in which the save file is located.
@@ Line 85: / Line 86: @@
 hkimscil # I don't twitt much . . . .
 jaemyung_lee # He does a lot!
+see https://dev.twitter.com/apps/new
 <code>#get your own one
@@ Line 111: / Line 116: @@
 df <- do.call("rbind", lapply(rdmTweets, as.data.frame))
-#dim(df)
+dim(df)
 library(tm)
@@ Line 123: / Line 128: @@
 # remove numbers
 myCorpus <- tm_map(myCorpus, removeNumbers)
-myCorpus <- tm_map(myCorpus, PlainTextDocument)
+# remove stopwords
+# keep "r" by removing it from stopwords
+myStopwords <- c(stopwords('english'), "available", "via")
+idx <- which(myStopwords == "r")
+myStopwords <- myStopwords[-idx]
+myCorpus <- tm_map(myCorpus, removeWords, myStopwords)
 # remove stopwords
@@ Line 131: / Line 141: @@
 myStopwords <- myStopwords[-idx]
 myCorpus <- tm_map(myCorpus, removeWords, myStopwords)
 dictCorpus <- myCorpus
@@ Line 142: / Line 153: @@
 myCorpus <- tm_map(myCorpus, stemCompletion, dictionary=dictCorpus)
 inspect(myCorpus[1:3])
-myDtm <- TermDocumentMatrix(myCorpus, control = list(minWordLength = 1))
 myDtm <- TermDocumentMatrix(myCorpus, control = list(minWordLength = 1))