安裝需要的packages
library(gutenbergr)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(stringr)
library(tidyr)
library(tidytext)
library(ggplot2)
library(wordcloud)
## Loading required package: RColorBrewer
library(reshape2)
##
## Attaching package: 'reshape2'
## The following object is masked from 'package:tidyr':
##
## smiths
快樂王子是悲慘的童話故事，灰姑娘結尾比較歡樂，欲比較兩種故事類型的用詞、情緒
#下載快樂王子，在書中第53~352行
book_prince <- gutenberg_download(30120) %>% filter(text!="") %>% distinct(gutenberg_id, text)
## Determining mirror for Project Gutenberg from http://www.gutenberg.org/robot/harvest
## Using mirror http://aleph.gutenberg.org
prince <- book_prince[53:352,]
#下載灰姑娘
cinderalla <- gutenberg_download(10830) %>% filter(text!="") %>%
distinct(gutenberg_id, text)
#快樂王子
#因為happy、prince會被切開使"happy"出現次數太多，會影響最後情緒分析
#把"happy prince"視為一個單詞
text<- paste0(prince$text, collapse = ' ') #把所有的文字接在一起
#gsub把正則表達式抓出來的字整個取代成happy prince
text <- gsub('(H|h)appy (P|p)rince','HappyPrince',text)
df <- tibble(text = text) #tibble存成dataframe
#快樂王子_word分列列出，去除stopwords，增加linenumber
tidy_prince <- df %>%
unnest_tokens(word, text) %>%
anti_join(stop_words)%>%
mutate(linenumber = row_number())
## Joining, by = "word"
#灰姑娘_word分列列出，去除stopwords，增加linenumber
tidy_Cinderalla <- cinderalla %>%
unnest_tokens(word, text) %>%
anti_join(stop_words) %>%
mutate(linenumber = row_number())
## Joining, by = "word"
#灰姑娘_用bing分析 觀察各章節情緒起伏
tidy_Cinderalla %>%
inner_join(get_sentiments("bing")) %>%
mutate(index= linenumber%/%30) %>%
group_by(index, sentiment) %>%
summarise(sum=n()) %>%
spread(sentiment, sum, fill = 0) %>%
mutate(sentiment = positive - negative) %>%
mutate(color = ifelse(sentiment < 0, "negative","positive")) %>%
ggplot(aes(x= index,y=sentiment)) +
geom_col(aes(fill = color)) +
geom_text(aes(label=sentiment))
## Joining, by = "word"
劇情先悲後喜
#快樂王子_用bing分析 觀察各章節情緒起伏
tidy_prince %>%
inner_join(get_sentiments("bing")) %>%
mutate(index= linenumber%/%30) %>%
group_by(index, sentiment) %>%
summarise(sum=n()) %>%
spread(sentiment, sum, fill = 0) %>%
mutate(sentiment = positive - negative) %>%
mutate(color = ifelse(sentiment < 0, "negative","positive")) %>%
ggplot(aes(x= index,y=sentiment)) +
geom_col(aes(fill = color)) +
geom_text(aes(label=sentiment))
## Joining, by = "word"
劇情最後很悲慘，所以負面詞也多很多
#快樂王子_比較用3個辭典有甚麼差別
prince_afinn <- tidy_prince %>%
inner_join(get_sentiments("afinn")) %>%
group_by(index = linenumber %/% 5) %>%
summarise(sentiment = sum(score)) %>%
mutate(method = "AFINN")
## Joining, by = "word"
prince_bing_and_nrc <- bind_rows(tidy_prince %>%
inner_join(get_sentiments("bing")) %>%
mutate(method = "Bing et al."),
tidy_prince %>%
inner_join(get_sentiments("nrc") %>%
filter(sentiment %in% c("positive",
"negative"))) %>%
mutate(method = "NRC")) %>%
count(method, index = linenumber %/% 5, sentiment) %>% #因長度不多，縮小微度
spread(sentiment, n, fill = 0) %>%
mutate(sentiment = positive - negative)
## Joining, by = "word"
## Joining, by = "word"
bind_rows(prince_afinn,
prince_bing_and_nrc) %>%
ggplot(aes(index, sentiment, fill = method)) +
geom_col(show.legend = FALSE) +
facet_wrap(~method, ncol = 1, scales = "free_y")
原本以為負面詞會很多，但其實還好，只有用Bing分析正負面的比例看起來差不多，可能跟字典收錄的詞有關
#灰姑娘_比較用3個辭典有甚麼差別
afinn <- tidy_Cinderalla %>%
inner_join(get_sentiments("afinn")) %>%
group_by(index = linenumber %/% 5) %>%
summarise(sentiment = sum(score)) %>%
mutate(method = "AFINN")
## Joining, by = "word"
bing_and_nrc <- bind_rows(tidy_Cinderalla %>%
inner_join(get_sentiments("bing")) %>%
mutate(method = "Bing et al."),
tidy_Cinderalla %>%
inner_join(get_sentiments("nrc") %>%
filter(sentiment %in% c("positive",
"negative"))) %>%
mutate(method = "NRC")) %>%
count(method, index = linenumber %/% 5, sentiment) %>%
spread(sentiment, n, fill = 0) %>%
mutate(sentiment = positive - negative)
## Joining, by = "word"
## Joining, by = "word"
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")
灰姑娘用三個辭典都是正面的多，在故事剛開始雖然比較悲慘，到中後面就歡樂的多
#快樂王子_畫出正負面的詞各有什麼字詞
prince_bing_word_counts <- tidy_prince %>%
inner_join(get_sentiments("bing")) %>%
count(word, sentiment, sort = TRUE) %>%
ungroup()
## Joining, by = "word"
prince_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()
## Selecting by n
快樂王子負面詞描述生活環境的較多，與故事內描述幫助窮人的情況相符
#灰姑娘_畫出正負面的詞各有什麼字詞
bing_word_counts <- tidy_Cinderalla %>%
inner_join(get_sentiments("bing")) %>%
count(word, sentiment, sort = TRUE) %>%
ungroup()
## Joining, by = "word"
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()
## Selecting by n
灰姑娘正負面的詞是較多在描述人上
poor,beautiful在兩本書出現頻率都很高，在灰姑娘中劇情用poor多用在可憐，在快樂王子則指窮人。觀察發現童話故事書的用字都較簡單、直接
#快樂王子內出現的字畫成文字雲
tidy_prince %>%
anti_join(stop_words) %>%
count(word,sort=TRUE) %>%
with(wordcloud(word, n, max.words = 100))
## Joining, by = "word"
#灰姑娘內出現的字次數畫成文字雲
tidy_Cinderalla %>%
anti_join(stop_words) %>%
count(word) %>%
with(wordcloud(word, n, max.words = 100))
## Joining, by = "word"
#快樂王子_正、負面的詞
tidy_prince %>%
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)
## Joining, by = "word"
#灰姑娘_正、負面的詞
tidy_Cinderalla %>%
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)
## Joining, by = "word"
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): stranger could not be fit on page. It will not be plotted.
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): troubles could not be fit on page. It will not be plotted.
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): tyrannical could not be fit on page. It will not be plotted.
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): uneasiness could not be fit on page. It will not be plotted.
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): unhappy could not be fit on page. It will not be plotted.
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): unworthy could not be fit on page. It will not be plotted.
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): wretched could not be fit on page. It will not be plotted.
## Warning in comparison.cloud(., colors = c("gray20", "gray80"), max.words =
## 100): yawn could not be fit on page. It will not be plotted.
