Data607 Wk10 assignment
angel
2024-03-31
#Task : recreate example code from chapter 2 , replicate using new corpus
#2.1 The sentiments datasets
library(tidytext)
get_sentiments("afinn")## # A tibble: 2,477 × 2
## word value
## <chr> <dbl>
## 1 abandon -2
## 2 abandoned -2
## 3 abandons -2
## 4 abducted -2
## 5 abduction -2
## 6 abductions -2
## 7 abhor -3
## 8 abhorred -3
## 9 abhorrent -3
## 10 abhors -3
## # ℹ 2,467 more rowsget_sentiments("bing")## # A tibble: 6,786 × 2
## word sentiment
## <chr> <chr>
## 1 2-faces negative
## 2 abnormal negative
## 3 abolish negative
## 4 abominable negative
## 5 abominably negative
## 6 abominate negative
## 7 abomination negative
## 8 abort negative
## 9 aborted negative
## 10 aborts negative
## # ℹ 6,776 more rowsyes
get_sentiments("nrc")## # A tibble: 13,872 × 2
## word sentiment
## <chr> <chr>
## 1 abacus trust
## 2 abandon fear
## 3 abandon negative
## 4 abandon sadness
## 5 abandoned anger
## 6 abandoned fear
## 7 abandoned negative
## 8 abandoned sadness
## 9 abandonment anger
## 10 abandonment fear
## # ℹ 13,862 more rows#2.2 Sentiment analysis with inner join
library(janeaustenr)
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, unionlibrary(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)nrc_joy <- get_sentiments("nrc") %>%
filter(sentiment == "joy")
tidy_books %>%
filter(book == "Emma") %>%
inner_join(nrc_joy) %>%
count(word, sort = TRUE)## Joining with `by = join_by(word)`## # A tibble: 301 × 2
## word n
## <chr> <int>
## 1 good 359
## 2 friend 166
## 3 hope 143
## 4 happy 125
## 5 love 117
## 6 deal 92
## 7 found 92
## 8 present 89
## 9 kind 82
## 10 happiness 76
## # ℹ 291 more rowslibrary(tidyr)
jane_austen_sentiment <- tidy_books %>%
inner_join(get_sentiments("bing")) %>%
count(book, index = linenumber %/% 80, sentiment) %>%
pivot_wider(names_from = sentiment, values_from = n, values_fill = 0) %>%
mutate(sentiment = positive - negative)## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("bing")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 435434 of `x` matches multiple rows in `y`.
## ℹ Row 5051 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.library(ggplot2)
ggplot(jane_austen_sentiment, aes(index, sentiment, fill = book)) +
geom_col(show.legend = FALSE) +
facet_wrap(~book, ncol = 2, scales = "free_x")
#2.3 Comparing the three sentiment dictionaries
pride_prejudice <- tidy_books %>%
filter(book == "Pride & Prejudice")
pride_prejudice## # A tibble: 122,204 × 4
## book linenumber chapter word
## <fct> <int> <int> <chr>
## 1 Pride & Prejudice 1 0 pride
## 2 Pride & Prejudice 1 0 and
## 3 Pride & Prejudice 1 0 prejudice
## 4 Pride & Prejudice 3 0 by
## 5 Pride & Prejudice 3 0 jane
## 6 Pride & Prejudice 3 0 austen
## 7 Pride & Prejudice 7 1 chapter
## 8 Pride & Prejudice 7 1 1
## 9 Pride & Prejudice 10 1 it
## 10 Pride & Prejudice 10 1 is
## # ℹ 122,194 more rowsafinn <- pride_prejudice %>%
inner_join(get_sentiments("afinn")) %>%
group_by(index = linenumber %/% 80) %>%
summarise(sentiment = sum(value)) %>%
mutate(method = "AFINN")## Joining with `by = join_by(word)`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) %>%
pivot_wider(names_from = sentiment,
values_from = n,
values_fill = 0) %>%
mutate(sentiment = positive - negative)## Joining with `by = join_by(word)`
## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("nrc") %>% filter(sentiment %in% : Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 215 of `x` matches multiple rows in `y`.
## ℹ Row 5178 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.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)## # A tibble: 2 × 2
## sentiment n
## <chr> <int>
## 1 negative 3316
## 2 positive 2308get_sentiments("bing") %>%
count(sentiment)## # A tibble: 2 × 2
## sentiment n
## <chr> <int>
## 1 negative 4781
## 2 positive 2005#2.4 Most common positive and negative words
bing_word_counts <- tidy_books %>%
inner_join(get_sentiments("bing")) %>%
count(word, sentiment, sort = TRUE) %>%
ungroup()## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("bing")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 435434 of `x` matches multiple rows in `y`.
## ℹ Row 5051 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.bing_word_counts## # A tibble: 2,585 × 3
## word sentiment n
## <chr> <chr> <int>
## 1 miss negative 1855
## 2 well positive 1523
## 3 good positive 1380
## 4 great positive 981
## 5 like positive 725
## 6 better positive 639
## 7 enough positive 613
## 8 happy positive 534
## 9 love positive 495
## 10 pleasure positive 462
## # ℹ 2,575 more rowsbing_word_counts %>%
group_by(sentiment) %>%
slice_max(n, n = 10) %>%
ungroup() %>%
mutate(word = reorder(word, n)) %>%
ggplot(aes(n, word, fill = sentiment)) +
geom_col(show.legend = FALSE) +
facet_wrap(~sentiment, scales = "free_y") +
labs(x = "Contribution to sentiment",
y = NULL)
custom_stop_words <- bind_rows(tibble(word = c("miss"),
lexicon = c("custom")),
stop_words)
custom_stop_words## # A tibble: 1,150 × 2
## word lexicon
## <chr> <chr>
## 1 miss custom
## 2 a SMART
## 3 a's SMART
## 4 able SMART
## 5 about SMART
## 6 above SMART
## 7 according SMART
## 8 accordingly SMART
## 9 across SMART
## 10 actually SMART
## # ℹ 1,140 more rows#2.5 Wordclouds
library(wordcloud)## Loading required package: RColorBrewertidy_books %>%
anti_join(stop_words) %>%
count(word) %>%
with(wordcloud(word, n, max.words = 100))## Joining with `by = join_by(word)`## Warning in wordcloud(word, n, max.words = 100): miss could not be fit on page.
## It will not be plotted.
library(reshape2)##
## Attaching package: 'reshape2'## The following object is masked from 'package:tidyr':
##
## smithstidy_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)## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("bing")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 435434 of `x` matches multiple rows in `y`.
## ℹ Row 5051 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.
Replicate with books from Charles dickens
library(gutenbergr)
# Display the first few rows of the metadata dataframe
glimpse(gutenberg_works())## Rows: 44,042
## Columns: 8
## $ gutenberg_id <int> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 21, 22,…
## $ title <chr> "The Declaration of Independence of the United Sta…
## $ author <chr> "Jefferson, Thomas", "United States", "Kennedy, Jo…
## $ gutenberg_author_id <int> 1638, 1, 1666, 3, 1, 4, NA, 3, 3, NA, 7, 7, 8, 18,…
## $ language <chr> "en", "en", "en", "en", "en", "en", "en", "en", "e…
## $ gutenberg_bookshelf <chr> "Politics/American Revolutionary War/United States…
## $ rights <chr> "Public domain in the USA.", "Public domain in the…
## $ has_text <lgl> TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TRUE, TR…#download books by charles dickens
cd <- gutenberg_works(author == "Dickens, Charles")
cd_works <- cd[cd$gutenberg_id > 42000, ]
cd_books <- gcd_books <- gutenberg_download(cd_works$gutenberg_id, meta_fields = "title")## Determining mirror for Project Gutenberg from https://www.gutenberg.org/robot/harvest## Using mirror http://aleph.gutenberg.org#tidy
cd_books <- cd_books %>%
mutate( linenumber = row_number(),
chapter = cumsum(str_detect(text, regex("^([\\divxlc])+$", ignore_case = TRUE)))) %>%
ungroup() %>%
unnest_tokens(word, text)cd_sentiment <- cd_books %>%
inner_join(get_sentiments("bing")) %>%
count(title, index = linenumber %/% 80, sentiment) %>%
pivot_wider(names_from = sentiment, values_from = n, values_fill = 0) %>%
mutate(sentiment = positive - negative)## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("bing")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 231097 of `x` matches multiple rows in `y`.
## ℹ Row 6710 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.#sentiment scores
library(ggplot2)
ggplot(cd_sentiment, aes(index, sentiment, fill = title)) +
geom_col(show.legend = FALSE) +
facet_wrap(~title, ncol = 2, scales = "free_x")
#Sentiment analysis with inner join
nrc_j <- get_sentiments("nrc") %>%
filter(sentiment == "joy")
cd_books %>%
filter(title == "A Child's Dream of a Star") %>%
inner_join(nrc_j) %>%
count(word, sort = TRUE)## Joining with `by = join_by(word)`## # A tibble: 29 × 2
## word n
## <chr> <int>
## 1 star 28
## 2 child 13
## 3 shining 8
## 4 angel 6
## 5 mother 5
## 6 god 4
## 7 beaming 3
## 8 baby 2
## 9 bless 2
## 10 daughter 2
## # ℹ 19 more rowsChilds_dream <- cd_books %>%
filter(title == "A Child's Dream of a Star")#compare the three sentiments
aff <- Childs_dream %>%
inner_join(get_sentiments("afinn")) %>%
group_by(index = linenumber %/% 80) %>%
summarise(sentiment = sum(value)) %>%
mutate(method = "AFINN")## Joining with `by = join_by(word)`bing_nrc <- bind_rows(
Childs_dream %>%
inner_join(get_sentiments("bing")) %>%
mutate(method = "Bing et al."),
Childs_dream %>%
inner_join(get_sentiments("nrc") %>%
filter(sentiment %in% c("positive",
"negative"))
) %>%
mutate(method = "NRC")) %>%
count(method, index = linenumber %/% 80, sentiment) %>%
pivot_wider(names_from = sentiment,
values_from = n,
values_fill = 0) %>%
mutate(sentiment = positive - negative)## Joining with `by = join_by(word)`
## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("nrc") %>% filter(sentiment %in% : Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 103 of `x` matches multiple rows in `y`.
## ℹ Row 4799 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.bind_rows(aff,
bing_nrc) %>%
ggplot(aes(index, sentiment, fill = method)) +
geom_col(show.legend = FALSE) +
facet_wrap(~method, ncol = 1, scales = "free_y")
#most common negative and positive words
word_counts <- cd_books %>%
inner_join(get_sentiments("bing")) %>%
count(word, sentiment, sort = TRUE) %>%
ungroup()## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("bing")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 231097 of `x` matches multiple rows in `y`.
## ℹ Row 6710 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.alot more positive words than negative
word_counts %>%
group_by(sentiment) %>%
slice_max(n, n = 10) %>%
ungroup() %>%
mutate(word = reorder(word, n)) %>%
ggplot(aes(n, word, fill = sentiment)) +
geom_col(show.legend = FALSE) +
facet_wrap(~sentiment, scales = "free_y") +
labs(x = "Contribution to sentiment",
y = NULL)
#word clouds
cd_books %>%
anti_join(stop_words) %>%
count(word) %>%
with(wordcloud(word, n, max.words = 100))## Joining with `by = join_by(word)`## Warning in wordcloud(word, n, max.words = 100): pickwick could not be fit on
## page. It will not be plotted.
cd_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)## Joining with `by = join_by(word)`## Warning in inner_join(., get_sentiments("bing")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 231097 of `x` matches multiple rows in `y`.
## ℹ Row 6710 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.