D607_A10_RickRN

Sentiment Analysis

In this assignment, use the primary example code in Text Mining in R - Chapter 2 Sentiment Analysis (Silge & Robinson, 2020) and extend the code in the following manner:
-Work with a different corpus of your choosing
-Incorporate at least 1 additional sentiment lexicon.

The NRC Word-Emotion Association Lexicon dataset is used in this code (Mohammad & Turney, 2013).

Reference: Silge, J., & Robinson, D. (2020). Text mining with R: A tidy approach. O’Reilly Media, Inc. Retrieved from https://www.tidytextmining.com/

Mohammad, S. M., & Turney, P. D. (2013). Crowdsourcing a word–emotion association lexicon. Computational Intelligence, 29(3), 436-465. Retrieved from https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1467-8640.2012.00460.x

A Journal of the Plague Year

A Journal of the Plague Year by Daniel Defoe from Gutenberg used as corpus. NRC Word-Emotion Association Lexicon dataset is used in this code (Mohammad & Turney, 2013).

The corpus will be tokenized and stop words will be removed.

The NRC lexicon used to identify tokens related to “fear” and “joy” found in the corpus in a plague.

A count of words related to fear and joy are ranked by frequency.

# comments
library(gutenbergr)

## Warning: package 'gutenbergr' was built under R version 4.0.3

library(tidytext)

## Warning: package 'tidytext' was built under R version 4.0.3

defoe <- gutenberg_download(c(376))  # A Journal of the Plague Year by Daniel Defoe

## Determining mirror for Project Gutenberg from http://www.gutenberg.org/robot/harvest

## Using mirror http://aleph.gutenberg.org

tidy_defoe <- defoe %>%
  unnest_tokens(word, text) %>%
  anti_join(stop_words)

## Joining, by = "word"

nrc_sentiments <- get_sentiments("nrc")

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

nrc_fear <- get_sentiments("nrc") %>%
  filter(sentiment == "fear")


(defoe_joy <- tidy_defoe %>%
  inner_join(nrc_joy) %>%
  count(word, sort = TRUE))

## Joining, by = "word"

## # A tibble: 174 x 2
##    word          n
##    <chr>     <int>
##  1 found       112
##  2 god          85
##  3 true         71
##  4 money        64
##  5 church       37
##  6 child        33
##  7 charity      32
##  8 abundance    27
##  9 pleased      25
## 10 mother       20
## # ... with 164 more rows

(defoe_fear <- tidy_defoe %>%
  inner_join(nrc_fear) %>%
  count(word, sort = TRUE))

## Joining, by = "word"

## # A tibble: 331 x 2
##    word          n
##    <chr>     <int>
##  1 plague      260
##  2 infection   162
##  3 god          85
##  4 dreadful     57
##  5 danger       54
##  6 death        52
##  7 die          42
##  8 fled         39
##  9 terrible     38
## 10 distress     35
## # ... with 321 more rows

Summary

Sentiment analysis provides a way to understand the attitudes and opinions expressed in texts. For example, in A Journal of the Plague Year, a search was made for the sentiments of fear and joy in a plague. Clearly, “plague” and “infection” are fear related words. However, some words can have dual meanings where “God” elicits both job and fear.