nrc emotions analysis

nrc_emotions.R

## installing and loading dependencies
if (!require("pacman")) install.packages("pacman")
pacman::p_load_current_gh(
    file.path('trinker', c(
        "gofastr",
        "textshape",
        "lexicon",
        "textclean",
        "termco"
    ))
)

pacman::p_load(magrittr)


## the data to tag
mytext <- c(
   'do you like it?  But I hate really bad dogs',
   'I am the best friend.',
   "Do you really like it?  I'm not a fan"
)


## make the nrc tokens
token_list <- lexicon::nrc_emotions %>%
    textshape::column_to_rownames() %>%
    t() %>%
    textshape::as_list()



## the procedure
counts <- mytext %>%
     textshape::split_sentence() %>%
     textshape::tidy_list('element', 'text') %$%
     termco::token_count(text, TRUE, token_list)

counts

## Coverage: 40% 
## # A tibble: 5 x 10
##      id n.tokens anger anticipation disgust  fear   joy sadness surprise trust
##   <int>    <dbl> <dbl>        <dbl>   <dbl> <dbl> <dbl>   <dbl>    <dbl> <dbl>
## 1     1        5     0            0       0     0     0       0        0     0
## 2     2        6     2            0       2     2     0       2        0     0
## 3     3        6     0            0       0     0     1       0        0     1
## 4     4        6     0            0       0     0     0       0        0     0
## 5     5        4     0            0       0     0     0       0        0     0

counts %>%
    dplyr::select(anger:trust) %>%
    textshape::as_list()


mytext %>%
     textshape::split_sentence() %>%
     textshape::tidy_list('element', 'text') %$%
     termco::token_count(text, element, token_list)


## Coverage: 66.67% 
## # A tibble: 3 x 10
##   element n.tokens     anger anticipation   disgust      fear       joy   sadness surprise     trust
##    <fctr>    <dbl>     <chr>        <chr>     <chr>     <chr>     <chr>     <chr>    <chr>     <chr>
## 1       1       11 2(18.18%)            0 2(18.18%) 2(18.18%)         0 2(18.18%)        0         0
## 2       2        6         0            0         0         0 1(16.67%)         0        0 1(16.67%)
## 3       3       10         0            0         0         0         0         0        0         0