Homework 7

Reproduce the book examples

# Load necessary libraries
library(tidytext)

Warning: package 'tidytext' was built under R version 4.5.3

library(janeaustenr)

Warning: package 'janeaustenr' was built under R version 4.5.3

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(ggplot2)

# Reproduction of Chapter 2: Sentiment analysis of Jane Austen's novels
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)

# Using the Bing lexicon to find sentiment trajectory
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.

# Visualizing the results
ggplot(jane_austen_sentiment, aes(index, sentiment, fill = book)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~book, ncol = 2, scales = "free_x") +
  labs(title = "Sentiment in Jane Austen's Novels",
       caption = "Source: Silge & Robinson, Text Mining with R")

pulling from the gutenbergr to download The War of the Worlds and The Time Machine

library(gutenbergr)

Warning: package 'gutenbergr' was built under R version 4.5.3

#Downloading 'The War of the Worlds' (36) and 'The Time Machine' (35)
wells_books <- gutenberg_download(c(35, 36), meta_fields = "title")

Using mirror https://aleph.pglaf.org.

tidy_wells <- wells_books %>%
  group_by(title) %>%
  mutate(linenumber = row_number()) %>%
  ungroup() %>%
  unnest_tokens(word, text)

#Getting a lexicon Loughran-McDonald
loughran <- get_sentiments("loughran")

wells_loughran <- tidy_wells %>%
  inner_join(loughran) %>%
  count(title, index = linenumber %/% 80, sentiment)

Joining with `by = join_by(word)`

Warning in inner_join(., loughran): Detected an unexpected many-to-many relationship between `x` and `y`.
ℹ Row 3326 of `x` matches multiple rows in `y`.
ℹ Row 2826 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.

ggplot(wells_loughran, aes(index, n, fill = sentiment)) +
  geom_col() +
  facet_wrap(~title, scales = "free_x") +
  labs(title = "Sentiment Complexity in H.G. Wells (Loughran Lexicon)",
       y = "Word Count",
       x = "Narrative Progress (80-line chunks)")