Executive Session 1 - Lab Assignment

[1] Assignment - Sentiment Analysis

• Provide a sentiment analysis on one of the books from the Harry Potter collection.

| | - philosophers_stone: Harry Potter and the Philosophers Stone (1997) - chamber_of_secrets: Harry Potter and the Chamber of Secrets (1998) - prisoner_of_azkaban: Harry Potter and the Prisoner of Azkaban (1999) - goblet_of_fire: Harry Potter and the Goblet of Fire (2000) - order_of_the_phoenix: Harry Potter and the Order of the Phoenix (2003) - half_blood_prince: Harry Potter and the Half-Blood Prince (2005) - deathly_hallows: Harry Potter and the Deathly Hallows (2007) |
|
- Capture your results below:

#install.packages("Rling")

library(Rling)
library(modeest)
#install.packages("textdata")
library(textdata)
#install.packages("tidytext")
library(tidytext)
library(knitr)


if (!require("tidyverse")) {
  install.packages("tidyverse")
  library(tidyverse)
}# data manipulation & plotting

## Loading required package: tidyverse

## Registered S3 method overwritten by 'httr':
##   method         from  
##   print.response rmutil

## ── Attaching packages ────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──

## ✔ ggplot2 3.2.0     ✔ purrr   0.3.2
## ✔ tibble  2.1.3     ✔ dplyr   0.8.3
## ✔ tidyr   0.8.3     ✔ stringr 1.4.0
## ✔ readr   1.3.1     ✔ forcats 0.4.0

## ── Conflicts ───────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()

if (!require("stringr")) {
  install.packages("stringr")
  library(stringr)
}# text cleaning and regular expressions

if (!require("tidytext")) {
  install.packages("tidytext")
  library(tidytext)
}# provides additional text mining functions

if (!require("harrypotter")) {
  install.packages("harrypotter")
  library(harrypotter)
}# provides the first seven novels of the Harry Potter series       

## Loading required package: harrypotter

if (!require("sentimentr")) {
  install.packages("sentimentr")
  library(sentimentr)
}

## Loading required package: sentimentr

if (!require("devtools")) {
  install.packages("devtools")
  library(devtools)
}

## Loading required package: devtools

## Loading required package: usethis

install_github('trinker/sentimentr')

## Skipping install of 'sentimentr' from a github remote, the SHA1 (645401e8) has not changed since last install.
##   Use `force = TRUE` to force installation

if (packageVersion("devtools") < 1.6) {
  install.packages("devtools")
}
devtools::install_github("bradleyboehmke/harrypotter")

## Skipping install of 'harrypotter' from a github remote, the SHA1 (51f71461) has not changed since last install.
##   Use `force = TRUE` to force installation

library(harrypotter)

str(prisoner_of_azkaban)

##  chr [1:22] "　　OWL POST　　Harry Potter was a highly unusual boy in many ways. For one thing, he hated the summer holidays"| __truncated__ ...

azkaban_sentences <- tibble(chapter = 1:length(prisoner_of_azkaban),
                       text = prisoner_of_azkaban) %>% 
  unnest_tokens(sentence, text, token = "sentences")

book_sentence <- azkaban_sentences %>%
  group_by(chapter) %>%
  mutate(sentence_num = 1:n(),
         index = round(sentence_num / n(), 2)) %>%
  unnest_tokens(word, sentence) %>%
  inner_join(get_sentiments("afinn")) %>%
  group_by(chapter, index) %>%
  summarise(sentiment = sum(value, na.rm = TRUE)) %>%
  arrange(desc(sentiment))

## Joining, by = "word"

book_sentence

## # A tibble: 1,848 x 3
## # Groups:   chapter [22]
##    chapter index sentiment
##      <int> <dbl>     <dbl>
##  1       4  0.01        13
##  2       1  0.49        12
##  3       4  0.9         12
##  4       5  0.87        12
##  5       6  0.75        12
##  6      11  0.87        12
##  7       5  0.88        11
##  8       8  0.07        11
##  9       8  0.45        11
## 10      11  0.56        11
## # … with 1,838 more rows

ggplot(book_sentence, aes(index, factor(chapter, levels = sort(unique(chapter), decreasing = TRUE)), fill = sentiment)) +
  geom_tile(color = "white") +
  scale_fill_gradient2() +
  scale_x_continuous(labels = scales::percent, expand = c(0, 0)) +
  scale_y_discrete(expand = c(0, 0)) +
  labs(x = "Chapter Progression", y = "Chapter") +
  ggtitle("Sentiment of Prisoner of Azkaban") +
  theme_minimal() +
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        legend.position = "top")