How similar is the musical taste of different countries? To answer this question we compared the percentage of daily hits similarities in 51 countries on Spotify. The analysis revealed 4 clear clusters, these are formed by:
1. Spanish speaking countries;
2. Most European countries, USA, Canada, Australia and New Zealand;
3. Most Asian countries.
Six countries (Brazil, Japan, Turkey, India, Australia and Italy) presented hits that did not clearly place them in these clusters. The most clearly distinctive of these was Brazil.
This project demonstrated for many Brazilians that the idea that the country is a major exporter of music is not currently valid. This was something unexpected for many and made the story have great reaction on social media.
The data was downloaded using Spotify’s API via R. The analysis was made in R. The graphics were produced in Adobe Illustrator.
What was the hardest part of this project?
The choice of visualization was the most challenging part. The decision for the radial display format allowed all distances to be shown simultaneously from a single central country while referring to a traditional format for viewing geographical distances, such as on an aviation radar. The simultaneous visualization of all distances between all countries (without a central option) was not prioritized because it produced too many distortions and excess of visual noise.
What can others learn from this project?
This project was able to test a clear hypothesis, that Brazil was musically isolated. In addition, we were able to identify clusters of countries defined by their musical tastes on Spotify’s hit charts.