Assignment 10A: Sentiment Analysis
Jacob Shapiro
2025-11-02
Prompt
In Text Mining with R, Chapter 2 (https://www.tidytextmining.com/sentiment.html) looks at Sentiment Analysis. In this assignment, you should start by getting the primary example code from chapter 2 working in an R Markdown document. You should provide a citation to this base code. You’re then asked to extend the code in two ways:
Work with a different corpus of your choosing, and Incorporate at least one additional sentiment lexicon (possibly from another R package that you’ve found through research).
Base code
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 rowsget_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 rowslibrary(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)
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")
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 2005bing_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 rowslibrary(wordcloud)## Warning: package 'wordcloud' was built under R version 4.5.2## 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.
p_and_p_sentences <- tibble(text = prideprejudice) %>%
unnest_tokens(sentence, text, token = "sentences")
p_and_p_sentences$sentence[2]## [1] "by jane austen"austen_chapters <- austen_books() %>%
group_by(book) %>%
unnest_tokens(chapter, text, token = "regex",
pattern = "Chapter|CHAPTER [\\dIVXLC]") %>%
ungroup()
austen_chapters %>%
group_by(book) %>%
summarise(chapters = n())## # A tibble: 6 × 2
## book chapters
## <fct> <int>
## 1 Sense & Sensibility 51
## 2 Pride & Prejudice 62
## 3 Mansfield Park 49
## 4 Emma 56
## 5 Northanger Abbey 32
## 6 Persuasion 25bingnegative <- get_sentiments("bing") %>%
filter(sentiment == "negative")
wordcounts <- tidy_books %>%
group_by(book, chapter) %>%
summarize(words = n())## `summarise()` has grouped output by 'book'. You can override using the
## `.groups` argument.tidy_books %>%
semi_join(bingnegative) %>%
group_by(book, chapter) %>%
summarize(negativewords = n()) %>%
left_join(wordcounts, by = c("book", "chapter")) %>%
mutate(ratio = negativewords/words) %>%
filter(chapter != 0) %>%
slice_max(ratio, n = 1) %>%
ungroup()## Joining with `by = join_by(word)`
## `summarise()` has grouped output by 'book'. You can override using the
## `.groups` argument.## # A tibble: 6 × 5
## book chapter negativewords words ratio
## <fct> <int> <int> <int> <dbl>
## 1 Sense & Sensibility 43 161 3405 0.0473
## 2 Pride & Prejudice 34 111 2104 0.0528
## 3 Mansfield Park 46 173 3685 0.0469
## 4 Emma 15 151 3340 0.0452
## 5 Northanger Abbey 21 149 2982 0.0500
## 6 Persuasion 4 62 1807 0.0343Me adding
Using gutenbergr package. Load Edgar Allan Poe volume 2
library(gutenbergr)## Warning: package 'gutenbergr' was built under R version 4.5.2#see options to download works
gut_options <- gutenberg_works(
languages = "en",
only_text = TRUE,
rights = c("Public domain in the USA.", "None"),
distinct = TRUE,
all_languages = FALSE,
only_languages = TRUE
)
#chose Edgar Allan Poe - The Works of Edgar Allan Poe — Volume 2
poe <- gutenberg_download(2148)## Determining mirror for Project Gutenberg from
## https://www.gutenberg.org/robot/harvest.
## Using mirror http://aleph.gutenberg.org.#clean up blank rows
poe_clean<- poe[!(poe$text == ""),]
#label each line as line number
poe_clean <- poe_clean %>% mutate(linenumber = row_number())
#take out all punctuation and special characters
poe_clean$text <- gsub("[^[:alnum:] ]", "", poe_clean$text)
#imported in fragments - split on spaces to make list of words
# poe_clean %>%
# mutate(split_values = str_split(text, "\\s+")) %>%
# unnest_wider(split_values, names_sep = " ")
poe_clean <- poe_clean %>% separate(text, into = c("word1", "word2", "word3", "word4", "word5","word6", "word7", "word8", "word9", "word10", "word11", "word12", "word13", "word14", "word15", "word16", "word17", "word18", "word19"), sep = "\\s+", extra = "merge", fill = "right")
#pivot into long list of words
poe_clean <- poe_clean %>% pivot_longer(cols = c("word1", "word2", "word3", "word4", "word5","word6", "word7", "word8", "word9", "word10", "word11", "word12", "word13", "word14", "word15", "word16", "word17", "word18", "word19"),
names_to = 'word_num',
values_to = "word")
#clean up blank and NA rows
poe_clean<- poe_clean[!(poe_clean$word == ""),]
poe_clean %>% na.omit()## # A tibble: 95,035 × 4
## gutenberg_id linenumber word_num word
## <int> <int> <chr> <chr>
## 1 2148 1 word1 The
## 2 2148 1 word2 Works
## 3 2148 1 word3 of
## 4 2148 1 word4 Edgar
## 5 2148 1 word5 Allan
## 6 2148 1 word6 Poe
## 7 2148 2 word1 by
## 8 2148 2 word2 Edgar
## 9 2148 2 word3 Allan
## 10 2148 2 word4 Poe
## # ℹ 95,025 more rowsSentiment Analysis
I can’t figure out how to assign the different works so trying to just do it as a whole
poe_sentiment <- poe_clean %>%
inner_join(get_sentiments("bing")) %>%
count(gutenberg_id, 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)`ggplot(poe_sentiment, aes(index, sentiment, fill = gutenberg_id)) +
geom_col(show.legend = FALSE) +
facet_wrap(~gutenberg_id, ncol = 2, scales = "free_x")
afinn <- poe_clean %>%
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(
poe_clean %>%
inner_join(get_sentiments("bing")) %>%
mutate(method = "Bing et al."),
poe_clean %>%
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 1746 of `x` matches multiple rows in `y`.
## ℹ Row 2153 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")
bing_word_counts <- poe_clean %>%
inner_join(get_sentiments("bing")) %>%
count(word, sentiment, sort = TRUE) %>%
ungroup()## Joining with `by = join_by(word)`bing_word_counts## # A tibble: 1,737 × 3
## word sentiment n
## <chr> <chr> <int>
## 1 well positive 96
## 2 great positive 86
## 3 like positive 79
## 4 fell negative 64
## 5 death negative 59
## 6 doubt negative 50
## 7 good positive 42
## 8 wild negative 40
## 9 right positive 38
## 10 scarcely negative 38
## # ℹ 1,727 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)