Assignment 10A: Sentiment Analysis

DATA 607 · Code Base

Author

Dillon Leeper

Published

November 8, 2026

Overview

Part 1 Reproduces Chapter 2 of Text Mining with R (Silge and Robinson): sentiment analysis of Jane Austen’s novels, using the book’s code unchanged
Part 2 Runs the same tests on The Great Gatsby (1925) and The Sun Also Rises (1926), adds a fourth method (sentimentr), and scores the scenes around each main character
Question Does the Chapter 2 approach tell the same story on two 1920s novels as it does on Austen?

Source: Silge, J., & Robinson, D. (2017). Text Mining with R: A Tidy Approach, Chapter 2, “Sentiment analysis with tidy data.” https://www.tidytextmining.com/sentiment.html. Original code: https://github.com/dgrtwo/tidy-text-mining.

Key findings

  • Tone: Gatsby is the only one of the eight books that scores negative overall. The Sun Also Rises is positive, but less so than any Austen novel.
  • Misread words: every book has one. “miss” (a title) for Austen and Gatsby, “damned” (used to mean “very”) for The Sun Also Rises.
  • Darkest chapter: found correctly for Gatsby (the Plaza fight and Myrtle’s death), wrong for The Sun Also Rises (a fishing trip, flagged because of a joke).
  • Sentence-level scoring: sentimentr fixes some negations (“not too pleasant”) and breaks others (“Don’t be a damned fool”).
  • Characters: in Gatsby, the scenes around Tom, Jordan, Myrtle and George Wilson lean negative. In The Sun Also Rises, everyone stays near neutral.

Details and numbers are in How the Results Differ from the Original.

Setup

Show code
library(tidytext)
library(janeaustenr)
library(dplyr)
library(stringr)
library(tidyr)
library(ggplot2)
library(wordcloud)
library(reshape2)
library(gutenbergr)
library(readr)
library(sentimentr)
library(knitr)
NoteBefore rendering

The AFINN and NRC lexicons download through the textdata package, which asks you to accept each license the first time. That prompt can’t be answered during a render, so run get_sentiments("afinn") and get_sentiments("nrc") once in the R console first. After that they load from the local cache.

Part 1: Reproducing Chapter 2

2.1 The sentiment lexicons

Three general-purpose lexicons, each scoring single words:

Lexicon How it scores a word
AFINN A number from -5 (very negative) to +5 (very positive)
Bing Positive or negative
NRC Positive or negative, plus eight emotions (anger, anticipation, disgust, fear, joy, sadness, surprise, trust)
Show code
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 rows
Show code
get_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 rows
Show code
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

Turn the Austen novels into one word per row, keeping track of the line and chapter each word came from.

Show code
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)

The most common “joy” words in Emma:

Show code
nrc_joy <- get_sentiments("nrc") %>% 
  filter(sentiment == "joy")

tidy_books %>%
  filter(book == "Emma") %>%
  inner_join(nrc_joy) %>%
  count(word, sort = TRUE)
# 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 rows

Net sentiment (positive words minus negative words) in each 80-line section of each novel, using Bing:

Show code
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)

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 lexicons

All three lexicons on Pride & Prejudice:

Show code
pride_prejudice <- tidy_books %>% 
  filter(book == "Pride & Prejudice")

afinn <- pride_prejudice %>% 
  inner_join(get_sentiments("afinn")) %>% 
  group_by(index = linenumber %/% 80) %>% 
  summarise(sentiment = sum(value)) %>% 
  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) %>%
  pivot_wider(names_from = sentiment,
              values_from = n,
              values_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")

The book’s explanation for why NRC runs higher than Bing: the two lexicons have different ratios of negative to positive words.

Show code
get_sentiments("nrc") %>% 
  filter(sentiment %in% c("positive", "negative")) %>% 
  count(sentiment)
sentiment n
negative 3316
positive 2308
Show code
get_sentiments("bing") %>% 
  count(sentiment)
sentiment n
negative 4781
positive 2005

2.4 Most common positive and negative words

Show code
bing_word_counts <- tidy_books %>%
  inner_join(get_sentiments("bing")) %>%
  count(word, sentiment, sort = TRUE) %>%
  ungroup()

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 rows
Show code
bing_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)

“miss” is scored negative, but Austen uses it as a title (“Miss Bennet”). The book’s fix is a custom stop word. Stop words are common words like “the” and “and” that get removed before counting, using anti_join(). Adding “miss” to that list means it gets removed too, so it can’t count as negative. The book builds the list here but doesn’t rerun anything with it. Part 2 applies it to Gatsby.

Show code
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

Show code
tidy_books %>%
  anti_join(stop_words) %>%
  count(word) %>%
  with(wordcloud(word, n, max.words = 100))

Show code
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)

2.6 Looking at units beyond words

Splitting into sentences and chapters instead of words:

Show code
p_and_p_sentences <- tibble(text = prideprejudice) %>% 
  unnest_tokens(sentence, text, token = "sentences")

p_and_p_sentences$sentence[2]
[1] "by jane austen"
Show code
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())
book chapters
Sense & Sensibility 51
Pride & Prejudice 62
Mansfield Park 49
Emma 56
Northanger Abbey 32
Persuasion 25

The most negative chapter in each novel, as a share of its words:

Show code
bingnegative <- get_sentiments("bing") %>% 
  filter(sentiment == "negative")

wordcounts <- tidy_books %>%
  group_by(book, chapter) %>%
  summarize(words = n())

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()
book chapter negativewords words ratio
Sense & Sensibility 43 161 3405 0.0472834
Pride & Prejudice 34 111 2104 0.0527567
Mansfield Park 46 173 3685 0.0469471
Emma 15 151 3340 0.0452096
Northanger Abbey 21 149 2982 0.0499665
Persuasion 4 62 1807 0.0343110

Part 2: Extending the Analysis

New corpus: two 1920s novels

The Great Gatsby The Sun Also Rises
Author F. Scott Fitzgerald Ernest Hemingway
Published 1925 1926
Project Gutenberg ID 64317 67138
US public domain since 2021 2022

Downloaded with gutenbergr. The first render saves a CSV copy, and later renders read from it, so the report doesn’t depend on the Gutenberg mirror.

Show code
book_titles <- c(`64317` = "The Great Gatsby", `67138` = "The Sun Also Rises")
books_file <- "gatsby_sun_also_rises.csv"

if (file.exists(books_file)) {
  raw_books <- read_csv(books_file, col_types = "ic", na = character())
} else {
  raw_books <- gutenberg_download(c(64317, 67138))
  write_csv(raw_books, books_file, na = "")
}

Cleaning

The book’s Austen chapter pattern doesn’t fit either book, so each gets its own rule:

The Great Gatsby The Sun Also Rises
Story starts at The second “I” (the first is in the table of contents) The first “CHAPTER”
Chapter headings A Roman numeral alone on a line “CHAPTER” on one line, the number on the next
Also dropped Title page, dedication, epigraph Front matter, “BOOK II/III” titles, transcriber’s note after “THE END”

Curly quotes and apostrophes are straightened so “don’t” matches the lexicons’ spelling.

Show code
new_books <- raw_books %>%
  mutate(
    book = factor(book_titles[as.character(gutenberg_id)], levels = book_titles),
    text = str_replace_all(text, "[‘’]", "'"),
    text = str_replace_all(text, "[“”]", '"'),
    trimmed = str_trim(text)
  ) %>%
  group_by(book) %>%
  mutate(
    start = if_else(book == "The Great Gatsby",
                    which(trimmed == "I")[2],
                    which(trimmed == "CHAPTER")[1]),
    end = coalesce(which(trimmed == "THE END")[1], n() + 1L)
  ) %>%
  filter(row_number() >= start, row_number() < end) %>%
  mutate(
    heading = if_else(book == "The Great Gatsby",
                      str_detect(trimmed, "^[IVX]+$"),
                      trimmed == "CHAPTER"),
    chapter = cumsum(heading)
  ) %>%
  filter(!heading,
         !str_detect(trimmed, "^BOOK [IVX]+$"),
         !str_detect(trimmed, "^\\d+$")) %>%
  mutate(linenumber = row_number()) %>%
  ungroup() %>%
  select(book, linenumber, chapter, text)

tidy_new <- new_books %>%
  unnest_tokens(word, text)

Check against the books (9 chapters in Gatsby, 19 in The Sun Also Rises):

Show code
new_books %>%
  group_by(Book = book) %>%
  summarise(Chapters = n_distinct(chapter),
            `First line of the story` = first(text[str_trim(text) != ""]))
Book Chapters First line of the story
The Great Gatsby 9 In my younger and more vulnerable years my father gave me some advice
The Sun Also Rises 19 Robert Cohn was once middleweight boxing champion of Princeton. Do not

Section size

The book scores 80-line sections and notes the right size depends on the text. These books have shorter lines than Austen’s:

Show code
section_size <- bind_rows(
  tibble(book = "Jane Austen (all 6 novels)",
         words = nrow(tidy_books),
         lines = nrow(austen_books())),
  tidy_new %>% count(book, name = "words") %>%
    left_join(new_books %>% count(book, name = "lines"), by = "book") %>%
    mutate(book = as.character(book))
) %>%
  mutate(words_per_line = words / lines)

section_size %>%
  transmute(Book = book,
            Words = format(words, big.mark = ","),
            Lines = format(lines, big.mark = ","),
            `Words per line` = round(words_per_line, 1))
Book Words Lines Words per line
Jane Austen (all 6 novels) 725,055 73,422 9.9
The Great Gatsby 48,636 6,357 7.7
The Sun Also Rises 68,305 10,110 6.8
Show code
austen_wpl <- section_size %>% filter(!book %in% book_titles) %>% pull(words_per_line)
new_wpl <- section_size %>% filter(book %in% book_titles) %>% pull(words_per_line)

new_section_size <- round(80 * austen_wpl / mean(new_wpl), -1)

Takeaway: the new books use 110-line sections, so each section holds about as much text as the book’s 80-line Austen sections. Pride & Prejudice stays at 80.

Sentiment through each novel

The Bing net-sentiment arc from Section 2.2, for the new books:

Show code
new_sentiment <- tidy_new %>%
  inner_join(get_sentiments("bing"), by = "word") %>%
  count(book, index = linenumber %/% new_section_size, sentiment) %>%
  pivot_wider(names_from = sentiment, values_from = n, values_fill = 0) %>%
  mutate(sentiment = positive - negative)

ggplot(new_sentiment, aes(index, sentiment, fill = book)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~book, ncol = 1, scales = "free_x") +
  labs(x = paste0(new_section_size, "-line section"), y = "Net sentiment (positive - negative)")

Sections that score negative
Austen (6 novels) 11% to 26%
The Great Gatsby 64%
The Sun Also Rises 33%

Takeaway: Austen’s arcs stay mostly above zero. Gatsby spends most of its length below.

Overall tone compared with Austen

All eight books, scored per 1,000 words so long and short books compare fairly:

Show code
all_tidy <- bind_rows(
  tidy_books %>% mutate(book = as.character(book), author = "Austen"),
  tidy_new %>% mutate(book = as.character(book),
                      author = if_else(book == "The Great Gatsby", "Fitzgerald", "Hemingway"))
)

bing_rates <- all_tidy %>%
  left_join(get_sentiments("bing"), by = "word") %>%
  group_by(author, book) %>%
  summarise(words = n(),
            matched = sum(!is.na(sentiment)),
            positive = sum(sentiment == "positive", na.rm = TRUE),
            negative = sum(sentiment == "negative", na.rm = TRUE),
            .groups = "drop")

nrc_rates <- all_tidy %>%
  inner_join(get_sentiments("nrc") %>% filter(sentiment %in% c("positive", "negative")),
             by = "word") %>%
  group_by(book) %>%
  summarise(nrc_positive_share = mean(sentiment == "positive"))

tone <- bing_rates %>%
  left_join(nrc_rates, by = "book") %>%
  mutate(matched_per_1k = matched / words * 1000,
         net_per_1k = (positive - negative) / words * 1000,
         bing_positive_share = positive / matched)

tone %>%
  arrange(desc(net_per_1k)) %>%
  transmute(Author = author,
            Book = book,
            `Net sentiment per 1,000` = round(net_per_1k, 1),
            `Sentiment words per 1,000` = round(matched_per_1k, 1),
            `Bing: % positive` = scales::percent(bing_positive_share, accuracy = 1),
            `NRC: % positive` = scales::percent(nrc_positive_share, accuracy = 1))
Author Book Net sentiment per 1,000 Sentiment words per 1,000 Bing: % positive NRC: % positive
Austen Persuasion 15.2 67.8 61% 70%
Austen Emma 14.6 74.3 60% 68%
Austen Mansfield Park 12.0 72.1 58% 66%
Austen Pride & Prejudice 11.5 71.2 58% 67%
Austen Sense & Sensibility 10.5 71.7 57% 65%
Austen Northanger Abbey 9.3 74.1 56% 65%
Hemingway The Sun Also Rises 5.6 50.8 56% 60%
Fitzgerald The Great Gatsby -5.9 57.6 45% 55%
  • Net sentiment: Austen 9.3 to 15.2 · Gatsby -5.9 · The Sun Also Rises 5.6
  • Sentiment words per 1,000: Austen 68 to 74 · Gatsby 58 · The Sun Also Rises 51
  • NRC runs higher than Bing (the book’s finding): true for all eight books

Takeaway: the new books have less sentiment vocabulary for the lexicons to work with, and Gatsby is the only negative book.

Adding a fourth method: sentimentr

The Chapter 2 lexicons score one word at a time, so “not good” counts as positive. sentimentr (Rinker), which the book mentions in Section 2.6, scores whole sentences and adjusts for nearby words:

Word type Example Effect
Negator “not” Flips the score
Amplifier “very” Strengthens it
De-amplifier “hardly” Weakens it

All four methods are scored on the same sections. For sentimentr, each section’s sentences are scored and summed.

Show code
score_sections <- function(lines, size = 80) {
  lines <- lines %>% mutate(index = linenumber %/% size)
  words <- lines %>% unnest_tokens(word, text)

  afinn_scores <- words %>%
    inner_join(get_sentiments("afinn"), by = "word") %>%
    group_by(book, index) %>%
    summarise(sentiment = sum(value), .groups = "drop") %>%
    mutate(method = "AFINN")

  bing_nrc_scores <- bind_rows(
    words %>%
      inner_join(get_sentiments("bing"), by = "word") %>%
      mutate(method = "Bing et al."),
    words %>%
      inner_join(get_sentiments("nrc") %>%
                   filter(sentiment %in% c("positive", "negative")),
                 by = "word") %>%
      mutate(method = "NRC")
  ) %>%
    count(book, method, index, sentiment) %>%
    pivot_wider(names_from = sentiment, values_from = n, values_fill = 0) %>%
    mutate(sentiment = positive - negative) %>%
    select(book, index, method, sentiment)

  sentimentr_scores <- lines %>%
    group_by(book, index) %>%
    summarise(text = str_squish(paste(text, collapse = " ")), .groups = "drop") %>%
    get_sentences() %>%
    sentiment() %>%
    as_tibble() %>%
    group_by(book, index) %>%
    summarise(sentiment = sum(sentiment, na.rm = TRUE), .groups = "drop") %>%
    mutate(method = "sentimentr")

  bind_rows(afinn_scores, bing_nrc_scores, sentimentr_scores) %>%
    mutate(method = factor(method,
                           levels = c("AFINN", "Bing et al.", "NRC", "sentimentr")))
}

pp_lines <- austen_books() %>%
  filter(book == "Pride & Prejudice") %>%
  mutate(linenumber = row_number(),
         chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]", ignore_case = TRUE))),
         book = "Pride & Prejudice")

section_scores <- bind_rows(
  score_sections(pp_lines),
  score_sections(new_books %>% mutate(book = as.character(book)), size = new_section_size)
) %>%
  mutate(book = factor(book, levels = c("Pride & Prejudice", book_titles)))

Each panel has its own scale. Compare the shape of the bars, not their height:

Show code
ggplot(section_scores, aes(index, sentiment, fill = method)) +
  geom_col(show.legend = FALSE) +
  facet_grid(method ~ book, scales = "free") +
  labs(x = "Section", y = "Section score")

Do the methods agree?

The book found the lexicons share the same ups and downs. Correlation measures that: 1 = they move together, 0 = no relationship.

Show code
agreement <- section_scores %>%
  pivot_wider(names_from = method, values_from = sentiment, values_fill = 0) %>%
  group_by(Book = book) %>%
  summarise(
    `AFINN vs Bing` = cor(AFINN, `Bing et al.`),
    `AFINN vs NRC` = cor(AFINN, NRC),
    `Bing vs NRC` = cor(`Bing et al.`, NRC),
    `sentimentr vs Bing` = cor(sentimentr, `Bing et al.`),
    `sentimentr vs AFINN` = cor(sentimentr, AFINN)
  )

agreement %>% mutate(across(-Book, ~ round(.x, 2)))
Book AFINN vs Bing AFINN vs NRC Bing vs NRC sentimentr vs Bing sentimentr vs AFINN
Pride & Prejudice 0.81 0.72 0.71 0.76 0.72
The Great Gatsby 0.77 0.60 0.63 0.68 0.59
The Sun Also Rises 0.80 0.70 0.56 0.68 0.69

Takeaway: average agreement between the three word lexicons is 0.75 on Pride & Prejudice, 0.67 on Gatsby and 0.69 on The Sun Also Rises. They still move together on the new books, just less closely.

Where word-level and sentence-level scoring disagree

Every sentence is scored twice, by Bing and by sentimentr, to see how often they point in opposite directions:

Show code
score_sentences <- function(lines) {
  sentences <- lines %>%
    group_by(book, chapter) %>%
    summarise(text = str_squish(paste(text, collapse = " ")), .groups = "drop") %>%
    get_sentences() %>%
    sentiment() %>%
    as_tibble() %>%
    transmute(book, chapter, sentence_id = row_number(), text = as.character(text),
              word_count, sentimentr = sentiment)

  bing_by_sentence <- sentences %>%
    select(sentence_id, text) %>%
    unnest_tokens(word, text) %>%
    inner_join(get_sentiments("bing"), by = "word") %>%
    group_by(sentence_id) %>%
    summarise(bing = sum(sentiment == "positive") - sum(sentiment == "negative"))

  sentences %>%
    left_join(bing_by_sentence, by = "sentence_id") %>%
    mutate(bing = coalesce(bing, 0L))
}

sentence_scores <- bind_rows(
  score_sentences(pp_lines),
  score_sentences(new_books %>% mutate(book = as.character(book)))
) %>%
  mutate(book = factor(book, levels = c("Pride & Prejudice", book_titles)))

disagreement <- sentence_scores %>%
  filter(bing != 0, sentimentr != 0) %>%
  group_by(book) %>%
  summarise(scored = n(), opposite = mean(sign(bing) != sign(sentimentr)))

disagreement %>%
  transmute(Book = book,
            `Sentences both methods scored` = format(scored, big.mark = ","),
            `Scored in opposite directions` = scales::percent(opposite, accuracy = 0.1))
Book Sentences both methods scored Scored in opposite directions
Pride & Prejudice 3,346 20.6%
The Great Gatsby 1,405 14.1%
The Sun Also Rises 2,428 17.5%

Examples with a negating word. Bing = positive minus negative words. sentimentr = the sentence score. Above 0 is positive for both.

Show code
negators <- "\\b(not|no|never|nothing|nobody|don't|didn't|isn't|wasn't|couldn't|wouldn't|can't)\\b"

examples <- sentence_scores %>%
  filter(book != "Pride & Prejudice",
         bing != 0, sign(bing) != sign(sentimentr),
         between(word_count, 5, 22),
         str_detect(str_to_lower(text), negators)) %>%
  group_by(book) %>%
  slice_max(abs(sentimentr), n = 4, with_ties = FALSE) %>%
  ungroup()

for (b in book_titles) {
  cat("\n\n**", b, "**\n\n", sep = "")
  examples %>%
    filter(book == b) %>%
    transmute(Sentence = text, Bing = bing, sentimentr = round(sentimentr, 2)) %>%
    knitr::kable() %>%
    print()
}

The Great Gatsby

Sentence Bing sentimentr
“I told her she might fool me but she couldn’t fool God. -2 0.49
He knew that Daisy was extraordinary, but he didn’t realize just how extraordinary a “nice” girl could be. 3 -0.49
“I just slip it on sometimes when I don’t care what I look like.” 1 -0.47
But he didn’t despise himself and it didn’t turn out as he had imagined. -1 0.45

The Sun Also Rises

Sentence Bing sentimentr
“But he’s not aficionado like you.” 1 -1.19
“But he’s not aficionado like you are.” 1 -1.11
This is all awfully amusing, but it’s not too pleasant. 1 -0.87
“Don’t be a damned fool.” -2 0.78
sentimentr gets it right sentimentr gets it wrong
“it’s not too pleasant”: reads the “not”, scores negative “Don’t be a damned fool”: the “don’t” flips the insult, scores positive

Takeaway: the two methods disagree on 14% to 18% of sentences in the new books (21% in Pride & Prejudice), and neither is consistently right.

Words that get misread

The Section 2.4 chart for each new book:

Show code
new_word_counts <- tidy_new %>%
  inner_join(get_sentiments("bing"), by = "word") %>%
  count(book, word, sentiment, sort = TRUE)

new_word_counts %>%
  group_by(book, sentiment) %>%
  slice_max(n, n = 10, with_ties = FALSE) %>%
  ungroup() %>%
  mutate(word = reorder_within(word, n, list(book, sentiment))) %>%
  ggplot(aes(n, word, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(book ~ sentiment, scales = "free") +
  scale_y_reordered() +
  labs(x = "Contribution to sentiment", y = NULL)

Gatsby: “miss” again

  • Top negative word: 38 uses
  • 31 of them are “Miss” + a name (mostly Miss Baker)

Applying the book’s custom stop word fix from Section 2.4:

Show code
net_per_1k <- function(tidy) {
  tidy %>%
    inner_join(get_sentiments("bing"), by = "word") %>%
    group_by(book) %>%
    summarise(net = sum(sentiment == "positive") - sum(sentiment == "negative")) %>%
    left_join(tidy_new %>% count(book, name = "words"), by = "book") %>%
    mutate(net_per_1k = net / words * 1000)
}

miss_fix <- bind_rows(
  net_per_1k(tidy_new) %>% mutate(version = "As scored"),
  net_per_1k(tidy_new %>% anti_join(custom_stop_words %>% filter(lexicon == "custom"), by = "word")) %>%
    mutate(version = "Without \"miss\"")
)

miss_fix %>%
  select(Book = book, version, net_per_1k) %>%
  mutate(net_per_1k = round(net_per_1k, 1)) %>%
  pivot_wider(names_from = version, values_from = net_per_1k)
Book As scored Without “miss”
The Great Gatsby -5.9 -5.1
The Sun Also Rises 5.6 5.6

Takeaway: Gatsby is still negative without “miss”, so the misread word isn’t what makes it negative.

The Sun Also Rises: “damned”

The characters use “damned” and “damn” to mean “very” (“damned good”), but Bing scores them negative. The word right after each one:

Show code
damned_bigrams <- new_books %>%
  filter(book == "The Sun Also Rises") %>%
  unnest_tokens(bigram, text, token = "ngrams", n = 2) %>%
  filter(!is.na(bigram)) %>%
  separate(bigram, c("word1", "word2"), sep = " ") %>%
  filter(word1 %in% c("damned", "damn")) %>%
  inner_join(get_sentiments("bing"), by = c("word2" = "word"))

damned_bigrams %>%
  count(`Next word is` = sentiment, name = "Times") %>%
  mutate(Share = scales::percent(Times / sum(Times), accuracy = 1))
Next word is Times Share
negative 18 35%
positive 34 65%
Show code
damned_bigrams %>%
  unite(Phrase, word1, word2, sep = " ") %>%
  count(Phrase, sort = TRUE) %>%
  head(8)
Phrase n
damned good 8
damn good 4
damned nice 4
damned well 4
damn nice 2
damned fine 2
damned hard 2
damn bad 1

Takeaway: the next word is positive 65% of the time, so “damned good” cancels to zero instead of counting as praise.

Wordclouds by sentiment

One cloud per book instead of the book’s split gray halves:

  • Size = how often the word appears
  • Color = AFINN score: red is negative, green is positive, darker is stronger
  • Stop words like “no” and “like” removed
Show code
cloud_colors <- c("#7f1d1d", "#991b1b", "#b91c1c", "#d62f2f", "#e05252",   # -5 to -1
                  "#888888",                                                # 0
                  "#3f9e5f", "#2f8a4f", "#237a42", "#166534", "#0f4d27")   # +1 to +5

sentiment_cloud <- function(tidy) {
  words <- tidy %>%
    anti_join(stop_words, by = "word") %>%
    inner_join(get_sentiments("afinn"), by = "word") %>%
    count(word, value, sort = TRUE) %>%
    head(100)
  set.seed(607)
  wordcloud(words$word, words$n,
            colors = cloud_colors[words$value + 6], ordered.colors = TRUE,
            random.order = FALSE, scale = c(4, 0.6))
}
Show code
sentiment_cloud(tidy_books)

Show code
sentiment_cloud(tidy_new %>% filter(book == "The Great Gatsby"))

Show code
sentiment_cloud(tidy_new %>% filter(book == "The Sun Also Rises"))

Most negative chapter in each book

The Section 2.6 test: the chapter with the highest share of negative words.

Show code
new_wordcounts <- tidy_new %>%
  count(book, chapter, name = "words")

new_negative <- tidy_new %>%
  semi_join(bingnegative, by = "word") %>%
  count(book, chapter, name = "negativewords") %>%
  left_join(new_wordcounts, by = c("book", "chapter")) %>%
  mutate(ratio = negativewords / words) %>%
  group_by(book) %>%
  slice_max(ratio, n = 1) %>%
  ungroup()

new_negative %>%
  transmute(Book = book, Chapter = chapter,
            `Negative words` = negativewords, Words = words,
            `Share negative` = scales::percent(ratio, accuracy = 0.1))
Book Chapter Negative words Words Share negative
The Great Gatsby 7 320 8839 3.6%
The Sun Also Rises 12 128 3981 3.2%

The top negative words in The Sun Also Rises’s pick:

Show code
tidy_new %>%
  filter(book == "The Sun Also Rises",
         chapter == new_negative$chapter[new_negative$book == "The Sun Also Rises"]) %>%
  semi_join(bingnegative, by = "word") %>%
  count(word, sort = TRUE) %>%
  head(10)
word n
hell 10
irony 10
pity 9
cold 8
falls 5
ironical 4
jam 4
steep 4
bait 3
bum 3
Book Chapter What happens Right call?
The Great Gatsby 7 The Plaza Hotel confrontation and Myrtle’s death Yes
The Sun Also Rises 12 The fishing trip in the mountains, one of the happiest stretches. Top “negative” words come from Bill’s “Irony and Pity” joke, plus “cold” and “falls” (waterfalls) No

Sentiment around each character

Names aren’t in any lexicon, so this scores the sentences that mention each character with sentimentr, then compares the share that read positive vs negative.

This measures This doesn’t measure
The mood of the scenes a character appears in Whether the character is good or bad
How the narrator describes them Sentences that use “he” or “she” instead of the name
How that mood changes chapter by chapter The narrators, Nick and Jake, who are mostly “I”
Show code
characters <- tribble(
  ~book,                ~character,        ~pattern,
  "The Great Gatsby",   "Gatsby",          "\\bgatsby",
  "The Great Gatsby",   "Daisy",           "\\bdaisy",
  "The Great Gatsby",   "Tom",             "\\btom\\b",
  "The Great Gatsby",   "Jordan",          "\\bjordan\\b|\\bmiss baker\\b",
  "The Great Gatsby",   "Myrtle",          "\\bmyrtle\\b|\\bmrs\\. wilson\\b",
  "The Great Gatsby",   "George Wilson",   "(?<!mrs\\. )\\bwilson\\b",
  "The Great Gatsby",   "Nick (narrator)", "\\bnick\\b|\\bcarraway\\b",
  "The Sun Also Rises", "Brett",           "\\bbrett\\b",
  "The Sun Also Rises", "Cohn",            "\\bcohn\\b|\\brobert\\b",
  "The Sun Also Rises", "Bill",            "\\bbill\\b",
  "The Sun Also Rises", "Mike",            "\\bmike\\b|\\bmichael\\b",
  "The Sun Also Rises", "Romero",          "\\bromero\\b",
  "The Sun Also Rises", "Montoya",         "\\bmontoya\\b",
  "The Sun Also Rises", "Jake (narrator)", "\\bjake\\b|\\bbarnes\\b"
)

new_sentences <- sentence_scores %>%
  filter(book != "Pride & Prejudice") %>%
  mutate(book = as.character(book), lower = str_to_lower(text))

character_sentences <- characters %>%
  inner_join(new_sentences, by = "book", relationship = "many-to-many") %>%
  filter(str_detect(lower, pattern))

character_summary <- character_sentences %>%
  group_by(book, character) %>%
  summarise(mentions = n(),
            positive = mean(sentimentr > 0),
            negative = mean(sentimentr < 0),
            .groups = "drop") %>%
  mutate(net = positive - negative)

book_baseline <- new_sentences %>%
  group_by(book) %>%
  summarise(net = mean(sentimentr > 0) - mean(sentimentr < 0))

The bar is the share of a character’s sentences that read positive minus the share that read negative. The dashed line is the whole book’s average.

Show code
character_summary %>%
  mutate(label = paste0(character, " (", mentions, ")"),
         label = reorder_within(label, net, book)) %>%
  ggplot(aes(net, label, fill = net > 0)) +
  geom_col(show.legend = FALSE) +
  geom_vline(data = book_baseline, aes(xintercept = net), linetype = "dashed") +
  facet_wrap(~book, ncol = 1, scales = "free_y") +
  scale_y_reordered() +
  scale_fill_manual(values = c(`TRUE` = "#2f8a4f", `FALSE` = "#d62f2f")) +
  scale_x_continuous(labels = scales::label_percent()) +
  labs(x = "% of sentences positive minus % negative",
       y = "Character (sentences that mention them)")

Show code
character_summary %>%
  arrange(book, net) %>%
  transmute(Book = book, Character = character, Mentions = mentions,
            `Read positive` = scales::percent(positive, accuracy = 1),
            `Read negative` = scales::percent(negative, accuracy = 1))
Book Character Mentions Read positive Read negative
The Great Gatsby Jordan 99 31% 52%
The Great Gatsby Tom 188 30% 46%
The Great Gatsby George Wilson 57 25% 40%
The Great Gatsby Myrtle 39 28% 41%
The Great Gatsby Gatsby 257 34% 32%
The Great Gatsby Daisy 185 40% 35%
The Great Gatsby Nick (narrator) 33 39% 12%
The Sun Also Rises Mike 281 23% 22%
The Sun Also Rises Cohn 278 23% 22%
The Sun Also Rises Romero 112 34% 30%
The Sun Also Rises Brett 431 26% 19%
The Sun Also Rises Montoya 54 30% 22%
The Sun Also Rises Jake (narrator) 146 27% 19%
The Sun Also Rises Bill 342 24% 16%

How the mood around the central characters changes chapter by chapter (chapters with at least 5 mentions):

Show code
central <- c("Gatsby", "Daisy", "Tom", "Brett", "Cohn", "Mike")

by_chapter <- character_sentences %>%
  filter(character %in% central) %>%
  group_by(book, character, chapter) %>%
  summarise(mentions = n(),
            net = mean(sentimentr > 0) - mean(sentimentr < 0),
            .groups = "drop") %>%
  filter(mentions >= 5)

line_labels <- by_chapter %>%
  group_by(book, character) %>%
  slice_max(chapter, n = 1)

ggplot(by_chapter, aes(chapter, net, color = character)) +
  geom_hline(yintercept = 0, color = "grey60") +
  geom_line() +
  geom_point(aes(size = mentions)) +
  geom_text(data = line_labels, aes(label = character),
            hjust = -0.25, size = 3.5, show.legend = FALSE) +
  facet_wrap(~book, ncol = 1, scales = "free_x") +
  scale_x_continuous(breaks = function(lims) seq(1, floor(lims[2] - 1.5), by = 1),
                     expand = expansion(add = c(0.3, 1.6))) +
  scale_y_continuous(labels = scales::label_percent()) +
  scale_size_area(max_size = 4, guide = "none") +
  labs(x = "Chapter", y = "% positive minus % negative") +
  theme(legend.position = "none")

  • Gatsby: the scenes around Jordan, Tom, George Wilson, and Myrtle lean negative. Of the sentences that mention Tom, 46% read negative and 30% positive.
  • After the Plaza: from chapter 7 on, Gatsby, Daisy and Tom all fall to zero or below.
  • The Sun Also Rises: every character falls between 0% and 8%. The lowest is Mike.
  • Cohn after the fight: from chapter 17 on, his sentences score -38%, compared with 8% before.

Takeaway: Gatsby’s negativity clusters around particular characters. The Sun Also Rises spreads its tone evenly across the whole group.

Gatsby vs The Sun Also Rises

The book’s comparison.cloud(), comparing the two books instead of positive and negative words. Color = which book (blue Gatsby, purple The Sun Also Rises), not sentiment. Bigger = used much more in that book.

Show code
set.seed(607)
tidy_new %>%
  anti_join(stop_words, by = "word") %>%
  count(word, book) %>%
  acast(word ~ book, value.var = "n", fill = 0) %>%
  comparison.cloud(colors = c("#2c5f8a", "#7b4fa6"),
                   max.words = 120, title.size = 1.4)

The Great Gatsby The Sun Also Rises
Net sentiment per 1,000 words -5.9 5.6
Sections that score negative 64% 33%
Sentiment words per 1,000 58 51
Lexicon agreement 0.67 0.69
Misread word “miss” (a title) “damned” (emphasis)
Most negative chapter 7, fits the plot 12, a misread joke
Characters Negativity clusters around a few Everyone near the book’s average

Takeaway: same era, very different results. The author’s style matters more than the decade.

How the Results Differ from the Original

Question from my approach Austen (Chapter 2) Gatsby and The Sun Also Rises
Overall tone Positive: 9.3 to 15.2 per 1,000 words Gatsby -5.9, Sun 5.6
Do the lexicons agree? Yes: 0.75 Less: 0.67 and 0.69
Does sentence-level scoring change things? Disagrees with Bing on 21% of sentences 14% to 18%, and not clearly better
The “miss” of the corpus “miss” “miss” (Gatsby), “damned” (Sun)
Darkest chapter Matches the plot in all six novels Right for Gatsby, wrong for Sun

Bottom line: the Chapter 2 method holds up on a book with dark events (Gatsby), but struggles with Hemingway’s sparse, joking dialogue. The biggest errors come from context (titles, swearing for emphasis, a running joke), which no word list can see.

Citations

Silge, J., & Robinson, D. (2017). Text mining with R: A tidy approach. O’Reilly Media. https://www.tidytextmining.com/sentiment.html

Silge, J., & Robinson, D. (2017). tidy-text-mining [Source code for the book]. GitHub. https://github.com/dgrtwo/tidy-text-mining

Rinker, T. W. (2021). sentimentr: Calculate text polarity sentiment [R package]. https://github.com/trinker/sentimentr

Nielsen, F. Å. (2011). A new ANEW: Evaluation of a word list for sentiment analysis in microblogs. Proceedings of the ESWC2011 Workshop on Making Sense of Microposts, 93–98. (AFINN lexicon)

Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 168–177. (Bing lexicon)

Mohammad, S. M., & Turney, P. D. (2013). Crowdsourcing a word–emotion association lexicon. Computational Intelligence, 29(3), 436–465. (NRC lexicon)

Fitzgerald, F. S. (1925). The great Gatsby. Project Gutenberg. https://www.gutenberg.org/ebooks/64317

Hemingway, E. (1926). The sun also rises. Project Gutenberg. https://www.gutenberg.org/ebooks/67138

AI Disclosure

Claude (Anthropic) helped write and test the code in this report, including the cleaning rules for the two books, the section-size adjustment, the four-method comparison, the sentence-level comparison and the character analysis. I chose the books, the extra lexicon, the questions in my approach and the idea to analyze the characters.

Anthropic. (2026). Claude [Large language model]. https://claude.ai/. Accessed November 8, 2026.