Chris Bail, Duke University
SICSS, Day 3
1) Corpus-Specific
2) General (e.g. LIWC)
3) Sentiment Analysis
my_negative_words<-c("failing","bad","badly",
"sad","angry","pathetic")
library(stringr)
Negative_Tweets<-Twitter_Dataset
[str_detect(Twitter_Dataset$tweets, my_negative_words),]
The quality of dictionary-based methods depends upon the match between the learning-corpus and the one you want to code.
The quality of dictionary-based methods depends upon the match between the learning-corpus and the one you want to code.
Creating your own is often a good solution, but it is very time intensive.