There will be expicit content within this document.

I will be looking at if .Paak’s music becomes more positive or negative as his relationship towards romance changes over this 3 year span. I will be looking at his three most popular albums “Malibu” (2016), “Oxnard” (2017), and “Ventura” (2019). I chose only to look at these works with the help of Genius https://genius.com and .Paak’s Genius profile, https://genius.com/artists/Anderson-paak. Genius has the all of his albums listed on its platform, but notes that “Malibu” (2016), “Oxnard” (2017), and “Ventura” (2019) are notably the most popular albums when looking at his discography. When looking under his Genius profile, the site does not bring much attention to his earlier EPs and albums, as he was not as known among music listeners. The songs on his earlier albums have very little information behind their meaning and are not publicized on Genius. With this said, Genius recognizes his fourth studio album, “Malibu” as his first to hit the charts and soar in popularity. Malibu is not nearly as popular as his latter two albums, but showcases his shift in tone as his career takes off. Using the most popular albums in my analysis will be useful to show how his reach to fans and his relationship to creating popular romantic, RnB style music changes as his fame grows. Looking at “Oxnard” (2018) and “Ventura” (2019) will help strengthen the claim that his style changed drastically through sentiment analysis of the positive and negative connotation behind the most popular words sung on each album. I will be looking at if the number of times .Paak uses words related to love and romance throughout each album. Observing the decrease in the use of words such as “love”, “hope”, and “baby” (to name a few examples) throughout his music as each album grows in popularity represents his change in mood and his image. I will be using the Genius API to get my information for this project.

First I have to download all the packages I will be using:

library(tidyverse)
library(tidytext)
library(textdata)
library(genius)
library(tibble)
library(knitr)
library(dplyr)
library(devtools)
library(wordcloud2)

I will download each album from the Genius API in order to analyze and compare the sentiment among each albums 20 most popular words. I will be looking at the change in tone from more romantic to more rap and exploring fame from Anderson .Paak’s first album to his most recent.

Lets begin with “Malibu”

According to Genius, Malibu is considered a “Popular Anderson .Paak Album”. According to Wikipedia https://en.wikipedia.org/wiki/Malibu_(album), “the album is described as the beginning of his potential commercial breakthrough, following his prominent role on Dr. Dre’s album Compton (2015)”, with whom he works with frequently. The album draws on his experience of escaping homelessness and finding love in California.

genius_album(artist= "Anderson .Paak", album= "Malibu")-> malibu

How many words are on Malibu?

malibu %>% 
  unnest_tokens(word, lyric) %>% 
  select(word) %>% 
  count()
## # A tibble: 1 x 1
##       n
##   <int>
## 1  7169

There are 7169 words.

Of those words, what are the 20 most used words on the album and how often are they seen?

malibu %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  filter(!word %in% c("tahm", "igh")) %>% 
  head(20) %>%
  knitr::kable()
word n
baby 37
time 35
love 32
feel 27
dreaming 25
momma 25
stop 24
carry 22
yeah 22
2 18
3 18
bed 18
heart 18
1 17
hey 17
life 14
ooh 14
girl 13
mmm 13
free 12

The three words that stuck out to me were “baby”, “time”, and “love”, as they clearly link to a more romantic mood which is seen throughout “Malibu”. .Paak clearly sings a lot on this album about his experience with love, considering it is the most popular word.

Lets look at the sentiment behind these words.

malibu %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  inner_join(get_sentiments("bing")) %>% 
  inner_join(get_sentiments("afinn")) %>% 
  filter(!word %in% c("tahm", "igh")) %>% 
  head(20) %>%
  knitr::kable()
word n sentiment value
love 32 positive 3
free 12 positive 1
afraid 9 negative -2
shit 9 negative -4
fuck 8 negative -4
pain 6 negative -2
bitch 5 negative -5
celebrate 5 positive 3
fake 5 negative -3
wrong 5 negative -2
cool 4 positive 1
damn 4 negative -4
top 4 positive 2
bad 3 negative -3
bullshit 3 negative -4
fucking 3 negative -4
perfect 3 positive 3
waste 3 negative -1
wow 3 positive 4
bright 2 positive 1

What stands out to me most:

“Love” is obviously seen a lot throughout the album (32 times with a sentiment value of 3), with positive sentiment, as well as “free” (which is seen 12 times on the album with a sentiment value of 1). “Pain” is only seen 6 times on the album with a sentiment value of -2. This strengthens the claim that this album revolves around .Paak’s experience with love and most likely how freeing it feels to be in love. This most likely had to be linked to becoming financially secure due to his rise in fame.

I created the data set “malibusentiment” with the code below and used it to create a graph that would demonstrate that the positive sentiment words are seen frequently throughout the album and are greater than the amount of negative sentiment words.

malibu %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  inner_join(get_sentiments("bing")) %>% 
  inner_join(get_sentiments("afinn")) %>% 
  filter(!word %in% c("tahm", "igh")) -> malibusentiment

The graph:

malibusentiment %>%
  arrange(desc(n)) %>%
  head(20) %>%
  ggplot(aes(word, value, fill= value)) + geom_col() +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))

A wordcloud will help visualize just how freqently the positive sentiment words are seen on “Malibu”.

malibu %>% 
  unnest_tokens(word, lyric) %>% 
  select(word) %>% 
  anti_join(stop_words) %>% 
  count(word, sort = TRUE) %>% 
  filter(!word %in% c("tahm", "igh")) %>% 
  wordcloud2()

“Time”, “baby”, “love”, and “dreaming” stand out among the other words within the word cloud.

“Oxnard”

This album pays homage to .Paak’s hometown of Oxnard, CA. The album definitely switches in tone from more romantic and slow songs, to faster paced, meticulous rap lyrics. It draws on experiences from the artist’s early life and lessons he has learned from his life in the spotlight. According to Oxnard Wikipedia, https://en.wikipedia.org/wiki/Oxnard_(album) “in contrast to previous albums, this wasn’t made while sofa-surfing to make ends meet. As Anderson .Paak puts it, he was eating calamari and lobster instead”.

genius_album(artist= 'Anderson .Paak', album= 'oxnard')-> oxnard

How many words are on Oxnard?

oxnard %>% 
  unnest_tokens(word, lyric) %>% 
  select(word) %>% 
  count()
## # A tibble: 1 x 1
##       n
##   <int>
## 1  8060

There are 8060 words on this album. That is a bit larger than the amount of words on Malibu.

Lets look at the most popular words on the album to see if there is any correlation to love and romance within this set of words…

oxnard %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  filter(!word %in% c("tahm", "igh")) %>% 
  head(20) %>%
  knitr::kable()
word n
left 56
shit 50
nigga 46
bitch 44
niggas 32
time 29
windows 28
ya 28
ooh 27
summers 25
tints 25
yeah 25
fuck 24
tinted 24
meet 23
gon 22
gotta 22
head 19
love 19
hold 17

The words that stuck out to me within this set were “left”, “shit”, and "n***a“, as they clearly link to a more angry and much less romantic mood which is noted about”Oxnard". This album differs from the first because Dr. Dre helped produce this album heavily, whereas on Malibu, it was primarily .Paak’s production. .Paak clearly sings/raps a lot on this album about his experience with his new found fame and fortune rather than love and relationships.

Let’s look at the sentiment analysis for “Oxnard”:

oxnard %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  inner_join(get_sentiments("bing")) %>% 
  inner_join(get_sentiments("afinn")) %>% 
  filter(!word %in% c("tahm", "igh")) %>% 
  head(20) %>%
  knitr::kable()
word n sentiment value
shit 50 negative -4
bitch 44 negative -5
fuck 24 negative -4
love 19 positive 3
free 11 positive 1
bullshit 9 negative -4
damn 9 negative -4
pain 9 negative -2
miss 7 negative -2
peace 7 positive 2
rich 7 positive 2
bad 6 negative -3
faith 5 positive 1
hate 5 negative -3
dick 4 negative -4
difficult 4 negative -1
fool 4 negative -2
foolish 4 negative -2
hard 4 negative -1
kill 4 negative -3

The first three words on the list have a negative sentiment! The words “shit” (value= -4), “bitch” (value= -5), and “fuck” (value= -4). This is very different from “Malibu” which had much more positive sentiment words. Could this have to do with Dr. Dre’s production on the album?

Using the code below, I created a data set for the 20 most popular words and their sentiment.

oxnard %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  inner_join(get_sentiments("bing")) %>% 
  inner_join(get_sentiments("afinn")) %>% 
  filter(!word %in% c("tahm", "igh")) -> oxnardsentiment

With the help of this data set I was able to create a graph to compare the positive sentiment and the negative sentiment on “Oxnard” to see which was greater.

The graph

oxnardsentiment %>%
  arrange(desc(n)) %>%
  ggplot(aes(n, sentiment, fill= sentiment)) + geom_col() +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))

This is the Oxnard word cloud which helps visualize this!

oxnard %>% 
  unnest_tokens(word, lyric) %>% 
  select(word) %>% 
  anti_join(stop_words) %>% 
  count(word, sort = TRUE) %>% 
  filter(!word %in% c("tahm", "igh")) %>% 
  wordcloud2()

“Ventura”

This is Anderson .Paak’s fourth studio album, but recognized by Genius as the last of his three most popular albums. Unlike “Malibu” and “Oxnard” .Paak chose to take more creative liberties on this album and rely on his own production skills rather than that of Dr. Dre. .Paak was able to explore his sound much more on this album and wrote the album while recording “Oxnard” in 2018. This album helped .Paak find his sound and his style without the tight production constraints.

genius_album(artist= "Anderson .Paak", album= "ventura")->ventura

Finally, the word count for “Ventura”…

ventura %>% 
  unnest_tokens(word, lyric) %>% 
  select(word) %>% 
  count()
## # A tibble: 1 x 1
##       n
##   <int>
## 1  4653

There are 4653 words on the album. Lets see what the 20 most popular words on “Ventura” were.

ventura %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  filter(!word %in% c("tahm", "igh")) %>% 
  head(20) %>%
  knitr::kable()
word n
ooh 90
ah 56
yeah 47
baby 38
coming 21
love 19
wanna 19
bah 18
gon 18
settle 18
stay 17
home 14
uh 14
feel 13
cha 12
cool 12
feels 12
lil 12
shake 12
woah 12

The top 3 words are “ooh”, “ah”, and “yeah”. These are not necesarily words because “ooh” and “ah” could also be classified as sounds, so I will also include the words “baby”, “coming” and “love” into the analysis of the most popular words on the album. We see that with more creative liberties, Anderson .Paak is back to singing about love! According to the Wikipedia page for Ventura https://en.wikipedia.org/wiki/Ventura_(Anderson_.Paak_album), it states, “the album is a lush ‘70s soul-inflected record. Last year’s Oxnard referenced his childhood in the titular Los Angeles neighborhood, while this latest album name-checks Ventura, the sun-kissed Californian coastal town in which, he’s explained, he ’found his depth’ as a teen.” Clearly this album draws on some serious emotions, whereas Oxnard focuses on his rise to fame.

This is the sentiment analysis of “Ventura”’s most popular words:

ventura %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  inner_join(get_sentiments("bing")) %>% 
  inner_join(get_sentiments("afinn")) %>% 
  filter(!word %in% c("tahm", "igh")) %>% 
  head(20) %>%
  knitr::kable()
word n sentiment value
love 19 positive 3
cool 12 positive 1
hard 7 negative -1
calm 6 positive 2
fun 6 positive 4
dumb 5 negative -3
shit 5 negative -4
crazy 4 negative -2
damn 4 negative -4
easy 4 positive 1
fuck 4 negative -4
lost 4 negative -3
miss 3 negative -2
broke 2 negative -1
broken 2 negative -1
fear 2 negative -2
hell 2 negative -4
honest 2 positive 2
pain 2 negative -2
super 2 positive 3

“Love” (with a sentiment value of 3), “cool”(with a sentiment value of 1), and “hard”(with a sentiment value of -1) are the three most popular positive sentiment words within the album. This could be drawing on .Paak’s teen years, as that is what the album centers around… yet still, “love” is the top contender for the most popular word. This is interesting to note when comparing the sentiment analysis of “Ventura” and “Malibu”. Both albums have the most popular word “love” with a positive sentiment, whereas “Oxanrd” seems to have much more negative sentiment.
Note: Could this have to do with a production change or is .Paak just drawing on different phases of his life?

Here is some code which helped to compile a graph of the amount of times the 20 most popular words are seen. This helps to visualize the sentiment analysis.

ventura %>%
  unnest_tokens(word, lyric) %>%
  select(word) %>%
  anti_join(stop_words) %>%
  count(word, sort = TRUE) %>%
  inner_join(get_sentiments("bing")) %>% 
  inner_join(get_sentiments("afinn")) %>% 
  filter(!word %in% c("tahm", "igh")) -> venturasentiment

The graph:

venturasentiment %>%
  head(20) %>%
  arrange(desc(n)) %>%
  ggplot(aes(word, n, fill= n)) + geom_col() +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))

“Love” and “cool” are serious outliers among the data… specifically “love” which is seen over 15 times!

Look at the word cloud for Ventura too:

ventura %>% 
  unnest_tokens(word, lyric) %>% 
  select(word) %>% 
  anti_join(stop_words) %>% 
  count(word, sort = TRUE) %>% 
  filter(!word %in% c("tahm", "igh")) %>% 
  wordcloud2()

Lastly, I want to compare all three albums just to see how the mood changes over the 3 year span they were created in. I created code to get the mean sentiment value of the words on all three albums with the code below.

mean(malibusentiment$value)->malibumean
mean(oxnardsentiment$value)->oxnardmean
mean(venturasentiment$value)->venturamean

The mean value for the albums were: “Malibu”= -0.35 “Oxnard”= -0.7058824 “Ventura”= -0.2075472

I then put all 3 sentiment value means into a data set with the code:

album <- c('Malibu', 'Oxnard', 'Ventura')
year <- c(2016, 2018, 2019)
meanvalue <- c("-0.35", "-0.7058824", "-0.2075472")

allmeans<- data.frame(album, year, meanvalue)

With these codes created, I was able to create a graph that would compare the mean sentiment values among the three albums which is shown below.

allmeans%>%
  arrange(desc(meanvalue))%>%
  ggplot(aes(album, meanvalue, fill= meanvalue)) + geom_col() +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))

In conclusion…

With all of the sentiment mean values in this graph, it is easy for me to conclude that there is a large mood shift from Anderson .Paak’s first album to his last. Knowing the general back story behind each album, it is no surprise that the two albums that .Paak had a heavier hand in producing revolve more around his experience in love and relationships, whereas “Oxnard” which Dr. Dre heavily produced is a more rap based album. When he has more creative liberty within his music and his producing, .Paak sings much more about love. Anderson .Paak’s relationship towards romance seens to stay pretty positive, with a dip seen through the “Oxnard” album. This could be attributed to him singing more about his then rise to fame and escaping poverty. I conclude that over the span of the three albums, Anderson .Paak’s relationship towards love shifts as any singer’s would. In “Malibu” he sings very heartfelt ballads about falling in love, living in poverty, and struggling to make ends meet. On “Oxnard” he focuses more on his monetary gains like any famous singer would, but on “Ventura” he shifts back into enjoying his relationships, which can clearly be seen in the graph above.