Sorry for Being Antisocial

For this project, I chose a rap album I know with a lot of words. I chose “Sorry for Being Antisocial” by Roddy Ricch. (Sorry in advance for some of the word results, rap albums are a bit vulgar).

library(geniusr)                         # This package gets lyrics
library(tidyverse)

── Attaching packages ────────────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──
✔ ggplot2 3.1.0     ✔ purrr   0.2.5
✔ tibble  2.0.0     ✔ dplyr   0.7.8
✔ tidyr   0.8.2     ✔ stringr 1.3.1
✔ readr   1.3.1     ✔ forcats 0.3.0
── Conflicts ───────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()

library(tidytext)
library(wordcloud2)

1. First I went through the process to get the information from the album and get the lyrics, then I went on to unnest them.

genius_token()

search_song("the box")

NA

get_song_meta(5068155)

antisocial_tracks <- scrape_tracklist(512452)

argument is not an atomic vector; coercing

antisocial_tracks

antisocial_lyrics <- map_df(antisocial_tracks$song_lyrics_url, scrape_lyrics_url)
antisocial_lyrics

NA

antisocial_words <- antisocial_lyrics %>%
  unnest_tokens(word, line) %>% 
  select(song_name, word)

antisocial_words

2. Next, I cleaned the lyrics by removing stopwords, and then created a table and word cloud with the word counts.

antisocial_words %>% 
  anti_join(get_stopwords()) %>% 
  count(word, sort = T)

Joining, by = "word"

antisocial_words %>% 
  anti_join(get_stopwords()) %>% 
  count(word, sort = T) %>%
  top_n(200) %>%
  wordcloud2(size = .5)

Joining, by = "word"
Selecting by n

3. Next I did a sentiment analyses using both bing and nrc, and created graphs of the words that contribute most to each sentiment.

bing <- get_sentiments("bing")
bing

antisocial_words %>% 
  inner_join(bing) %>% 
  count(word, sentiment, sort = TRUE) %>%
  group_by(sentiment) %>%
  top_n(10) %>%
  ungroup() %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(vars(sentiment), scales = "free") +
  labs(y = "Roddy Ricch Sorry for Being Antisocial album: Words that contribute the most to each sentiment",
       x = NULL) +
  scale_fill_viridis_d() +
  coord_flip() +
  theme_minimal()

Joining, by = "word"
Selecting by n

antisocial_words %>% 
  inner_join(nrc) %>% 
  count(word, sentiment, sort = TRUE) %>%
  group_by(sentiment) %>%
  top_n(5) %>%
  ungroup() %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(vars(sentiment), scales = "free") +
  labs(y = "Roddy Ricch Sorry for Being Antisocial album: Words that contribute the most to each sentiment",
       x = NULL) +
  scale_fill_viridis_d() +
  coord_flip() +
  theme_minimal()

Joining, by = "word"
Selecting by n

4. Next I created bigrams of the lyrics, removed the stopwords, and created a table and word cloud of the most common bigrams.

antisocial_lyrics %>%
  unnest_tokens(bigram, line, token = "ngrams", n = 2) %>% 
  select(bigram)

NA

antisocial_lyrics %>%
  unnest_tokens(bigram, line, token = "ngrams", n = 2) %>% 
  select(bigram) -> antisocial_bigrams

antisocial_bigrams %>% 
  separate(bigram, c("word1", "word2"), sep = " ") %>% 
  filter(!word1 %in% stop_words$word) %>%
  filter(!word2 %in% stop_words$word) %>% 
  unite(bigram, word1, word2, sep = " ")

NA

antisocial_bigrams %>% 
  separate(bigram, c("word1", "word2"), sep = " ") %>% 
  filter(!word1 %in% stop_words$word) %>%
  filter(!word2 %in% stop_words$word) %>% 
  unite(bigram, word1, word2, sep = " ") %>%
  count(bigram, sort = T) %>%
  filter(n > 1) %>% 
  wordcloud2(size = .5)

5. Lastly, I used the bigram method to find the most common words that came after the words he/she.

first_word <- c("he", "she")                                  

antisocial_bigrams %>% 
  count(bigram, sort = T) %>% 
  separate(bigram, c("word1", "word2"), sep = " ") %>%       
  filter(word1 %in% first_word) %>%                          
  count(word1, word2, wt = n, sort = TRUE) %>% 
  rename(total = nn) %>%
  mutate(word2 = factor(word2, levels = rev(unique(word2)))) %>%    
  group_by(word1) %>% 
  top_n(5) %>% 
  ggplot(aes(word2, total, fill = word1)) +                         
  scale_fill_viridis_d() +                                          
  geom_col(show.legend = FALSE) +
  labs(x = NULL, y = NULL, title = "Word following:") +
  facet_wrap(~word1, scales = "free") +
  coord_flip() +
  theme_minimal()

Selecting by total