Sentiment Scoring

gistfile1.txt

if (!require("pacman")) install.packages("pacman")
pacman::p_load_gh("trinker/stansent", 'wrathematics/meanr')
pacman::p_load(syuzhet, qdap, sentimentr, microbenchmark, RSentiment)

ase <- c(
    "I haven't been sad in a long time.",
    "I am extremely happy today.",
    "It's a good day.",
    "But suddenly I'm only a little bit happy.",
    "Then I'm not happy at all.",
    "In fact, I am now the least happy person on the planet.",
    "There is no happiness left in me.",
    "Wait, it's returned!",
    "I don't feel so bad after all!"
)

syuzhet <- setNames(as.data.frame(lapply(c("bing", "afinn", "nrc"),
    function(x) get_sentiment(ase, method=x))), c("bing", "afinn", "nrc"))


left_just(data.frame(
    stanford = sentiment_stanford(ase)[["sentiment"]],
    hu_liu = round(sentiment(ase, question.weight = 0)[["sentiment"]], 2),
    sentiword = round(sentiment(ase, sentiword, question.weight = 0)[["sentiment"]], 2),    
    RSentiment = calculate_score(ase), 
    meanr = score(ase)$score,
    syuzhet,
    sentences = ase,
    stringsAsFactors = FALSE
), "sentences")


##   stanford hu_liu sentiword RSentiment meanr bing afinn nrc sentences                                              
## 1     -0.5   0.35      0.18         -1    -1   -1    -2   0 I haven't been sad in a long time.                     
## 2        1    0.8      0.65          1     1    1     3   1 I am extremely happy today.                            
## 3      0.5    0.5      0.32          1     1    1     3   1 It's a good day.                                       
## 4     -0.5      0         0          0     1    1     3   1 But suddenly I'm only a little bit happy.              
## 5     -0.5  -0.41     -0.56         -1     1    1     3   1 Then I'm not happy at all.                             
## 6     -0.5   0.06      0.11          1     1    1     3   1 In fact, I am now the least happy person on the planet.
## 7     -0.5  -0.38     -0.05         -1     1    1     2   1 There is no happiness left in me.                      
## 8        0      0     -0.14          0     0    0     0  -1 Wait, it's returned!                                   
## 9     -0.5   0.38      0.24         -1    -1   -1    -3  -1 I don't feel so bad after all!  


ase_100 <- rep(ase, 100)

stanford <- function() {sentiment_stanford(ase_100)}

sentimentr_hu_liu <- function() sentiment(ase_100)
sentimentr_sentiword <- function() sentiment(ase_100, sentiword) 

RSentiment <- function() calculate_score(ase_100) 

syuzhet_binn <- function() get_sentiment(ase_100, method="bing")
syuzhet_nrc <- function() get_sentiment(ase_100, method="nrc")
syuzhet_afinn <- function() get_sentiment(ase_100, method="afinn")

meanr <- function() score(ase_100)$score

microbenchmark(
    stanford(),
    sentimentr_hu_liu(),
    sentimentr_sentiword(),
    RSentiment(), 
    meanr(),
    syuzhet_binn(), 
    syuzhet_nrc(),
    syuzhet_afinn(),
    times = 5
)

## Unit: milliseconds
##                    expr          min          lq         mean       median           uq          max neval cld
##              stanford() 26049.630509 26582.16834 28061.970376 26608.887503 27728.346567 33340.818958     5   b
##     sentimentr_hu_liu()   236.048823   272.29553   274.037475   272.853871   286.759067   302.230087     5  a 
##  sentimentr_sentiword()   959.647424  1024.73664  1047.736414  1051.780539  1057.367660  1145.149809     5  a 
##            RSentiment()   694.730641   699.80786   708.982585   705.759142   718.520967   726.094312     5  a 
##                 meanr()     1.356034     1.63808     1.717397     1.835142     1.874143     1.883586     5  a 
##          syuzhet_binn()   391.055432   394.30121   402.412862   395.948732   396.496400   434.262537     5  a 
##           syuzhet_nrc()   897.140547   925.76382   948.401006   943.427158   965.656997  1010.016505     5  a 
##         syuzhet_afinn()   166.468647   169.91313   173.710105   171.194853   177.713094   183.260804     5  a