Last active
October 3, 2017 11:49
-
-
Save almogsi/8ad7ad8c677989a38663b0189ffaf4d0 to your computer and use it in GitHub Desktop.
NoVAD is the Norms of Valence, Arousal and Dominance (Warriner, Kuperman & Brysbaert , 2013). The function takes a string as an argument and returns the mean value of valence, arousal and dominance.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| novad <- read.csv("Download_NoVAD_csv.csv") #Change for you local csv file | |
| novad$Word <- as.character(novad$Word) | |
| library(stringr) | |
| library(tm) | |
| NoVAD <- function(a){ | |
| a <- as.character(a) | |
| sms_corpus <- Corpus(VectorSource(a)) | |
| #translate all letters to lower case | |
| clean_corpus <- tm_map(sms_corpus, tolower) | |
| # remove numbers | |
| clean_corpus <- tm_map(clean_corpus, removeNumbers) | |
| # remove punctuation | |
| clean_corpus <- tm_map(clean_corpus, removePunctuation) | |
| clean_corpus <- tm_map(clean_corpus, stripWhitespace) | |
| b <- strsplit(clean_corpus[[1]]$content, " ") | |
| b <- unlist(b) | |
| sums_c <- double(length(b)) | |
| sums_d <- double(length(b)) | |
| sums_e <- double(length(b)) | |
| for (i in 1:length(b)){ | |
| M_str <- str_detect(b[i], novad$Word)==T | |
| M_char <- nchar(b[i])==nchar(novad$Word) | |
| c <- sum(novad$V.Mean.Sum[M_char*M_str==T]) #valence | |
| d <- sum(novad$A.Mean.Sum[M_char*M_str==T]) #arousal | |
| e <- sum(novad$D.Mean.Sum[M_char*M_str==T]) #dominance | |
| sums_c[i] <- c | |
| sums_d[i] <- d | |
| sums_e[i] <- e | |
| } | |
| valence <- sum(sums_c)/length(sums_c[sums_c>0]) | |
| arousal <- sum(sums_d)/length(sums_d[sums_d>0]) | |
| dominance <- sum(sums_e)/length(sums_e[sums_e>0]) | |
| return(c(valence, arousal, dominance)) | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment