Introduction

The task for this week is to obtain the primary example code from Chapter 2 in Text Mining with R, extend it with a different corpus and incorporate one additional sentiment lexicon.

Citiation

The code and examples used in this document are adapted from: Silge, J., & Robinson, D. (2017). Tidy Text Mining with R. O’Reilly Media, Inc. Chapter 2. https://www.tidytextmining.com/sentiment.html

library(tidytext)
library(janeaustenr)
library(dplyr)
## 
## 载入程辑包：'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)
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
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
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
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)
nrc_joy <- get_sentiments("nrc") %>% 
  filter(sentiment == "joy")
tidy_books %>%
  filter(book == "Emma") %>%
  inner_join(nrc_joy) %>%
  count(word, sort = TRUE)
## Joining with `by = join_by(word)`
## # 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
library(tidyr)
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.
library(ggplot2)
ggplot(jane_austen_sentiment, aes(index, sentiment, fill = book)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~book, ncol = 2, scales = "free_x")

pride_prejudice <- tidy_books %>% 
  filter(book == "Pride & Prejudice")
pride_prejudice
## # A tibble: 122,204 × 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 is       
## # ℹ 122,194 more rows
afinn <- pride_prejudice %>% 
  inner_join(get_sentiments("afinn")) %>% 
  group_by(index = linenumber %/% 80) %>% 
  summarise(sentiment = sum(value)) %>% 
  mutate(method = "AFINN")
## Joining with `by = join_by(word)`
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)
## Joining with `by = join_by(word)`
## Joining with `by = join_by(word)`
## Warning in inner_join(., get_sentiments("nrc") %>% filter(sentiment %in% : 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.
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")

get_sentiments("nrc") %>% 
  filter(sentiment %in% c("positive", "negative")) %>% 
  count(sentiment)
## # A tibble: 2 × 2
##   sentiment     n
##   <chr>     <int>
## 1 negative   3316
## 2 positive   2308
get_sentiments("bing") %>% 
  count(sentiment)
## # A tibble: 2 × 2
##   sentiment     n
##   <chr>     <int>
## 1 negative   4781
## 2 positive   2005
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
## # 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
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)

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
library(wordcloud)
## 载入需要的程辑包：RColorBrewer
tidy_books %>%
  anti_join(stop_words) %>%
  count(word) %>%
  with(wordcloud(word, n, max.words = 100))
## Joining with `by = join_by(word)`

library(reshape2)
## 
## 载入程辑包：'reshape2'
## The following object is masked from 'package:tidyr':
## 
##     smiths
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.

p_and_p_sentences <- tibble(text = prideprejudice) %>% 
  unnest_tokens(sentence, text, token = "sentences")
p_and_p_sentences$sentence[2]
## [1] "by jane austen"
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                25
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 0.0343

Extention

I chose to incorporate the Loughran sentiment lexicon as an additional sentiment lexicon

get_sentiments("loughran")
## # A tibble: 4,150 × 2
##    word         sentiment
##    <chr>        <chr>    
##  1 abandon      negative 
##  2 abandoned    negative 
##  3 abandoning   negative 
##  4 abandonment  negative 
##  5 abandonments negative 
##  6 abandons     negative 
##  7 abdicated    negative 
##  8 abdicates    negative 
##  9 abdicating   negative 
## 10 abdication   negative 
## # ℹ 4,140 more rows
loughran_positive <- get_sentiments("loughran") %>% 
  filter(sentiment == "positive")
tidy_books %>%
  filter(book == "Mansfield Park") %>%
  inner_join(loughran_positive) %>%
  count(word, sort = TRUE)
## Joining with `by = join_by(word)`
## # A tibble: 150 × 2
##    word          n
##    <chr>     <int>
##  1 good        326
##  2 great       199
##  3 better      151
##  4 happy       117
##  5 best        102
##  6 pleasure    101
##  7 happiness    86
##  8 able         68
##  9 perfectly    48
## 10 strong       47
## # ℹ 140 more rows
loughran_sentiment <- tidy_books %>%
  inner_join(get_sentiments("loughran")) %>%
  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("loughran")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 1252 of `x` matches multiple rows in `y`.
## ℹ Row 2772 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(loughran_sentiment, aes(index, sentiment, fill = book)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~book, ncol = 2, scales = "free_x")

get_sentiments("loughran") %>% 
  filter(sentiment %in% c("positive", "negative", "uncertainty", "litigious")) %>% 
  count(sentiment)
## # A tibble: 4 × 2
##   sentiment       n
##   <chr>       <int>
## 1 litigious     904
## 2 negative     2355
## 3 positive      354
## 4 uncertainty   297
loughran_word_total <- tidy_books %>%
  inner_join(get_sentiments("loughran")) %>%
  count(word, sentiment, sort = TRUE) %>%
  ungroup()
## Joining with `by = join_by(word)`
## Warning in inner_join(., get_sentiments("loughran")): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 1252 of `x` matches multiple rows in `y`.
## ℹ Row 2772 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.
loughran_word_total
## # A tibble: 1,374 × 3
##    word    sentiment       n
##    <chr>   <chr>       <int>
##  1 could   uncertainty  3613
##  2 miss    negative     1855
##  3 good    positive     1380
##  4 might   uncertainty  1369
##  5 great   positive      981
##  6 may     uncertainty   956
##  7 shall   litigious     834
##  8 better  positive      639
##  9 happy   positive      534
## 10 perhaps uncertainty   491
## # ℹ 1,364 more rows
loughran_word_total %>%
  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)

suppressWarnings(
tidy_books %>%
  inner_join(get_sentiments("loughran")) %>%
  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)`

Conclusion

By leveraging multiple lexicons, we can capture a wider range of sentiments and nuances present in textual data, leading to more accurate and insightful analyses.