Difference between revisions of "R: sentiments analysis"
Jump to navigation
Jump to search
Onnowpurbo (talk | contribs) |
Onnowpurbo (talk | contribs) |
||
| Line 29: | Line 29: | ||
inner_join(nrcjoy) %>% | inner_join(nrcjoy) %>% | ||
count(word, sort = TRUE) | 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") | ||
| + | |||
| + | |||
Revision as of 17:01, 8 November 2018
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")