Top Songs of the 2010’s
Photo by Austin Neill on Unsplash
Top 5 Songs
| Decade Rank | Title | Artist | Genre | Year |
|---|---|---|---|---|
| 1 | bad guy | Billie Eilish | electropop | 2019 |
| 2 | 7 rings | Ariana Grande | dance pop | 2019 |
| 3 | Old Town Road - Remix | Lil Nas X | country rap | 2019 |
| 4 | Señorita | Shawn Mendes | canadian pop | 2019 |
| 5 | rockstar (feat. 21 Savage) | Post Malone | dfw rap | 2018 |
Most Popular Genres
Here are the genre types that make up the top songs of the decade:
With almost half of 2010’s Top 100 songs fitting into the ‘dance pop’ genre, this represents what popular music sounded like in the decade. ‘Big room’ is a subgenre of electronic house music, and comes in second to the popularity of ‘dance pop’.
What Makes a Song Popular
Let’s unpack what actually made a song popular in the 2010’s. What elements of the music were important for it to be liked by the masses throughout a whole decade? To explore this, I ran a stepwise regression on all the audio features Spotify provided for the Top 100 songs of the 2010’s, with popularity as the dependent variable.
After running the analysis, we are left with the following co-efficients for a regression formula:
\[
popularity = 89.05 + (-.21)(energy) + (0.17)(speechiness)
\]
This equation lets us make the inference that in the 2010’s, the audio features of a track that contributed to it being popular were energy and speechiness. More specifically, a song being lower in energy and higher in speechiness would make it more popular.
A summary of the stepwise analysis is presented below:
##
## Call:
## lm(formula = popularity ~ energy + speechiness, data = spotify_data_clean %>%
## filter(decade == decade_input))
##
## Residuals:
## Min 1Q Median 3Q Max
## -41.373 -3.951 1.305 5.254 12.777
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 89.04530 3.85469 23.101 < 2e-16 ***
## energy -0.21344 0.05251 -4.065 9.78e-05 ***
## speechiness 0.16995 0.10919 1.556 0.123
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 8.467 on 97 degrees of freedom
## Multiple R-squared: 0.1719, Adjusted R-squared: 0.1549
## F-statistic: 10.07 on 2 and 97 DF, p-value: 0.0001062