R: sentiments analysis

library(tidytext)
sentiments

get_sentiments("afinn")
get_sentiments("bing")
get_sentiments("nrc")

library(janeaustenr)
library(dplyr)
library(stringr)
tidy_books <- austen_books() %>%
    group_by(book) %>%
    mutate(linenumber = row_number(),
           chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]",
           ignore_case = TRUE)))) %>%
           ungroup() %>%
    unnest_tokens(word, text)

nrcjoy <- get_sentiments("nrc") %>%
    filter(sentiment == "joy")
tidy_books %>%
    filter(book == "Emma") %>%
    inner_join(nrcjoy) %>%
    count(word, sort = TRUE)

library(tidyr)
janeaustensentiment <- tidy_books %>%
    inner_join(get_sentiments("bing")) %>%
    count(book, index = linenumber %/% 80, sentiment) %>%
    spread(sentiment, n, fill = 0) %>%
    mutate(sentiment = positive - negative)

library(ggplot2)
ggplot(janeaustensentiment, aes(index, sentiment, fill = book)) +
    geom_col(show.legend = FALSE) +
    facet_wrap(~book, ncol = 2, scales = "free_x")

pride_prejudice <- tidy_books %>%
    filter(book == "Pride & Prejudice")
pride_prejudice

afinn <- pride_prejudice %>%
    inner_join(get_sentiments("afinn")) %>%
    group_by(index = linenumber %/% 80) %>%
    summarise(sentiment = sum(score)) %>%
    mutate(method = "AFINN")
bing_and_nrc <- bind_rows(
    pride_prejudice %>%
       inner_join(get_sentiments("bing")) %>%
       mutate(method = "Bing et al."),
    pride_prejudice %>%
       inner_join(get_sentiments("nrc") %>%
       filter(sentiment %in% c("positive",
                               "negative"))) %>%
       mutate(method = "NRC")) %>%
       count(method, index = linenumber %/% 80, sentiment) %>%
       spread(sentiment, n, fill = 0) %>%
       mutate(sentiment = positive - negative)

bind_rows(afinn,
          bing_and_nrc) %>%
    ggplot(aes(index, sentiment, fill = method)) +
          geom_col(show.legend = FALSE) +
          facet_wrap(~method, ncol = 1, scales = "free_y")

get_sentiments("nrc") %>%
    filter(sentiment %in% c("positive",
                            "negative")) %>%
    count(sentiment)

get_sentiments("bing") %>%
    count(sentiment)

bing_word_counts <- tidy_books %>%
    inner_join(get_sentiments("bing")) %>%
    count(word, sentiment, sort = TRUE) %>%
    ungroup()
bing_word_counts

bing_word_counts %>%
    group_by(sentiment) %>%
    top_n(10) %>%
    ungroup() %>%
    mutate(word = reorder(word, n)) %>%
ggplot(aes(word, n, fill = sentiment)) +
       geom_col(show.legend = FALSE) +
       facet_wrap(~sentiment, scales = "free_y") +
       labs(y = "Contribution to sentiment",
            x = NULL) +
       coord_flip()

Pranala Menarik

• R