Geographical maps using Shazam Recognitions

Shazam is a mobile app that can be asked to identify a song by making it “listen”’ to a piece of music. Due to its immense popularity, the organization’s name quickly turned into a verb used in regular conversation (“Do you know this song? Let’s Shazam it.“). A successful identification is referred to as a Shazam recognition.

Shazam users can opt-in to anonymously share their location data with Shazam. Umar Hansa used to work for Shazam and decided to plot the geospatial data of 1 billion Shazam recognitions, during one of the company’s “hackdays“. The following wonderful city, country, and world maps are the result.

All visualisations (source) follow the same principle: Dots, representing successful Shazam recognitions, are plotted onto a blank geographical coordinate system. Can you guess the cities represented by these dots?

These first maps have an additional colour coding for operating systems. Can you guess which is which?

Blue dots represent iOS (Apple iPhones) and seem to cluster in the downtown area’s whereas red Android phones dominate the zones further from the city centres. Did you notice something else? Recall that Umar used a blank canvas, not a map from Google. Nevertheless, in all visualizations the road network is clearly visible. Umar guesses that passengers (hopefully not the drivers) often Shazam music playing in the car.

Try to guess the Canadian and American cities below and compare their layout to the two European cities that follow.

The maps were respectively of Toronto, San Fransisco, London, and Paris. It is just amazing how accurate they resemble the actual world. You have got to love the clear Atlantic borders of Europe in the world map below.

Are iPhones less common (among Shazam users) in Southern and Eastern Europe? In contrast, England and the big Japanese and Russian cities jump right out as iPhone hubs. In order to allow users to explore the data in more detail, Umar created an interactive tool comparing his maps to Google’s maps. A publicly available version you can access here (note that you can zoom in).This required quite complex code, the details of which are in his blog. For now, here is another, beautiful map of England, with (the density of) Shazam recognitions reflected by color intensity on a dark background.

London is so crowded! New York also looks very cool. Central Park, the rivers and the bay are so clearly visible, whereas Governors Island is completely lost on this map.

If you liked this blog, please read Umar’s own blog post on this project for more background information, pieces of the JavaScript code, and the original images. If you which to follow his work, you can find him on Twitter.

EDIT — Here and here you find an alternative way of visualizing geographical maps using population data as input for line maps in the R-package ggjoy.