R: sentiments analysis - Revision history

Onnowpurbo at 10:35, 8 November 2018

2018-11-08T10:35:13Z

2018-11-08T10:32:34Z

2018-11-08T10:30:26Z

2018-11-08T10:25:53Z

2018-11-08T10:21:50Z

2018-11-08T10:01:04Z

2018-11-08T09:58:44Z

2018-11-08T09:57:03Z

2018-11-08T09:56:02Z

2018-11-08T09:53:36Z

Created page with " library(tidytext) sentiments ==Pranala Menarik== * R"

New page

library(tidytext)
sentiments

==Pranala Menarik==

* [[R]]

← Older revision		Revision as of 10:35, 8 November 2018
Line 116:		Line 116:
	count(word) %>%		count(word) %>%
	with(wordcloud(word, n, max.words = 100))		with(wordcloud(word, n, max.words = 100))
		+
		+
		+	library(reshape2)
		+	tidy_books %>%
		+	inner_join(get_sentiments("bing")) %>%
		+	count(word, sentiment, sort = TRUE) %>%
		+	acast(word ~ sentiment, value.var = "n", fill = 0) %>%
		+	comparison.cloud(colors = c("gray20", "gray80"),
		+	max.words = 100)
		+

← Older revision	Revision as of 10:32, 8 November 2018
Line 105:	Line 105:


	+	custom_stop_words <- bind_rows(data_frame(word = c("miss"),
	+	lexicon = c("custom")),
	+	stop_words)
	+	custom_stop_words


−	+	library(wordcloud)
	+	tidy_books %>%
	+	anti_join(stop_words) %>%
	+	count(word) %>%
	+	with(wordcloud(word, n, max.words = 100))

@@ Line 101: / Line 101: @@
          facet_wrap(~sentiment, scales = "free_y") +
          labs(y = "Contribution to sentiment",
-        x = NULL) +
+             x = NULL) +
          coord_flip()

← Older revision		Revision as of 10:25, 8 November 2018
Line 76:		Line 76:
	geom_col(show.legend = FALSE) +		geom_col(show.legend = FALSE) +
	facet_wrap(~method, ncol = 1, scales = "free_y")		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()
		+
		+
		+
		+
		+

← Older revision	Revision as of 10:21, 8 November 2018
Line 45:	Line 45:


	+
	+	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")

← Older revision		Revision as of 10:01, 8 November 2018
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")
		+
		+

@@ Line 13: / Line 13: @@
   library(dplyr)
   library(stringr)
   tidy_books <- austen_books() %>%
       group_by(book) %>%
@@ Line 22: / Line 21: @@
       unnest_tokens(word, text)

@@ Line 16: / Line 16: @@
   tidy_books <- austen_books() %>%
       group_by(book) %>%
-        mutate(linenumber = row_number(),
+     mutate(linenumber = row_number(),
-               chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]",
+            chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]",
-               ignore_case = TRUE)))) %>%
+            ignore_case = TRUE)))) %>%
-               ungroup() %>%
+            ungroup() %>%
-        unnest_tokens(word, text)
+     unnest_tokens(word, text)
 ==Pranala Menarik==
 * [[R]]

← Older revision		Revision as of 09:56, 8 November 2018
Line 5:		Line 5:


		+	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)

	==Pranala Menarik==		==Pranala Menarik==

	* [[R]]		* [[R]]