Week 10 - NLP Part 1
Keith Colella
2023-04-02
Reperformance of Textbook Exercises
We begin by re-performing the text mining and sentiment analysis from Chapter 2 of Silge and Robinson’s “Text Mining with R” (https://www.tidytextmining.com/). I’ve directly leveraged the code and snippets of explanatory text from their book.
In Part 2, I’ll complete the assignment by extending the analysis to another corpus.
Set-up
library(tidyverse)
library(tidytext)
library(textdata)
library(janeaustenr)
library(wordcloud)
library(reshape2)
library(lexicon)
library(httr)The function get_sentiments() allows us to get specific
sentiment lexicons with the appropriate measures for each one.
afinn <- get_sentiments('afinn')
bing <- get_sentiments('bing')
nrc <- get_sentiments('nrc')Sentiment analysis with inner join
Let’s also set up some other columns to keep track of which line and
chapter of the book each word comes from; we use group_by
and mutate to construct those columns.
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)What are the most common joy words in Emma? Let’s use
count() from dplyr.
nrc_joy <- nrc %>%
filter(sentiment == "joy")
tidy_books %>%
filter(book == "Emma") %>%
inner_join(nrc_joy) %>%
count(word, sort = TRUE) %>%
head(1)## Joining with `by = join_by(word)`## # A tibble: 1 × 2
## word n
## <chr> <int>
## 1 good 359Next, we count up how many positive and negative words there are in
defined sections of each book. We define an index here to
keep track of where we are in the narrative; this index (using integer
division) counts up sections of 80 lines of text.
jane_austen_sentiment <- tidy_books %>%
inner_join(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(., 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.Now we can plot these sentiment scores across the plot trajectory of
each novel. Notice that we are plotting against the index
on the x-axis that keeps track of narrative time in sections of
text.
library(ggplot2)
ggplot(jane_austen_sentiment, aes(index, sentiment, fill = book)) +
geom_col(show.legend = FALSE) +
facet_wrap(~book, ncol = 2, scales = "free_x")
Sentiment through the narratives of Jane Austen’s novels
Comparing the three sentiment dictionaries
First, let’s use filter() to choose only the words from
the one novel we are interested in.
pride_prejudice <- tidy_books %>%
filter(book == "Pride & Prejudice")
pride_prejudice %>% head(10)## # A tibble: 10 × 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 isNow, we can use inner_join() to calculate the sentiment
in different ways.
pride_afinn <- pride_prejudice %>%
inner_join(afinn) %>%
group_by(index = linenumber %/% 80) %>%
summarise(sentiment = sum(value)) %>%
mutate(method = "AFINN")## Joining with `by = join_by(word)`pride_bing_and_nrc <- bind_rows(
pride_prejudice %>%
inner_join(bing) %>%
mutate(method = "Bing et al."),
pride_prejudice %>%
inner_join(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(., nrc %>% filter(sentiment %in% c("positive", "negative"))): 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.Comparing three sentiment lexicons using Pride and Prejudice
bind_rows(pride_afinn,
pride_bing_and_nrc) %>%
ggplot(aes(index, sentiment, fill = method)) +
geom_col(show.legend = FALSE) +
facet_wrap(~method, ncol = 1, scales = "free_y")
(ref:comparecap)
Let’s look briefly at how many positive and negative words are in these lexicons.
nrc %>%
filter(sentiment %in% c("positive", "negative")) %>%
count(sentiment)## # A tibble: 2 × 2
## sentiment n
## <chr> <int>
## 1 negative 3316
## 2 positive 2308bing %>%
count(sentiment)## # A tibble: 2 × 2
## sentiment n
## <chr> <int>
## 1 negative 4781
## 2 positive 2005Both lexicons have more negative than positive words, but the ratio of negative to positive words is higher in the Bing lexicon than the NRC lexicon. This will contribute to the effect we see in the plot above, as will any systematic difference in word matches, e.g. if the negative words in the NRC lexicon do not match the words that Jane Austen uses very well. Whatever the source of these differences, we see similar relative trajectories across the narrative arc, with similar changes in slope, but marked differences in absolute sentiment from lexicon to lexicon. This is all important context to keep in mind when choosing a sentiment lexicon for analysis.
Most common positive and negative words
By implementing count() here with arguments of both
word and sentiment, we find out how much each
word contributed to each sentiment.
bing_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 %>% head(10)## # A tibble: 10 × 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 462This can be shown visually, and we can pipe straight into ggplot2, if we like, because of the way we are consistently using tools built for handling tidy data frames.
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)
Words that contribute to positive and negative sentiment in Jane Austen’s novels
If it were appropriate for our purposes, we could easily add “miss”
to a custom stop-words list using bind_rows(). We could
implement that with a strategy such as this.
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 rowsWordclouds
Let’s look at the most common words in Jane Austen’s works as a whole again, but this time as a wordcloud in Figure @ref(fig:firstwordcloud).
tidy_books %>%
anti_join(stop_words) %>%
count(word) %>%
with(wordcloud(word, n, max.words = 100))## Joining with `by = join_by(word)`
The most common words in Jane Austen’s novels
You may need to turn the data frame into a matrix with reshape2’s
acast(). Until the step where we need to send the data to
comparison.cloud(), this can all be done with joins,
piping, and dplyr because our data is in tidy format.
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)## 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.
Most common positive and negative words in Jane Austen’s novels
Looking at units beyond just words
R packages included coreNLP [@R-coreNLP], cleanNLP [@R-cleanNLP], and sentimentr [@R-sentimentr] are examples of such sentiment analysis algorithms. For these, we may want to tokenize text into sentences, and it makes sense to use a new name for the output column in such a case.
p_and_p_sentences <- tibble(text = prideprejudice) %>%
unnest_tokens(sentence, text, token = "sentences")Let’s look at just one.
p_and_p_sentences$sentence[2]## [1] "by jane austen"The sentence tokenizing does seem to have a bit of trouble with UTF-8
encoded text. Use unnest_tokens() is to split into tokens
using a regex pattern.
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 25First, let’s get the list of negative words from the Bing lexicon. Second, let’s make a data frame of how many words are in each chapter so we can normalize for the length of chapters. Then, let’s find the number of negative words in each chapter and divide by the total words in each chapter. For each book, which chapter has the highest proportion of negative words?
bingnegative <- 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 0.0343Summary
Sentiment analysis provides a way to understand the attitudes and opinions expressed in texts. In this chapter, we explored how to approach sentiment analysis using tidy data principles; when text data is in a tidy data structure, sentiment analysis can be implemented as an inner join. We can use sentiment analysis to understand how a narrative arc changes throughout its course or what words with emotional and opinion content are important for a particular text. We will continue to develop our toolbox for applying sentiment analysis to different kinds of text in our case studies later in this book.