Take a look

The World Beat

World Radio

Spotify LogoFree 30sec preview provided by Spotify. Full track

Latest Tweet

World Mood

World Mood Map

Trending artists

How it works

#1 It analyzes what people all over the world are posting on Twitter with the hashtag #nowplaying (last 500 tweets) and tries to extract the artists and songs played using some heuristics.

#3 It plays a TOP song (Spotify 30 secs preview) by this target artist and at the end of the song the process restarts, analyzing again the last 500 tweets, computing the target artist and playing a song.

#2 Using artist similarities measures it chooses an artist that would be a good compromise for the music tastes of the people, in that moment, considering what they posted in the last 500 tweets.

#4 Every two seconds a graph representing the "world beat" is refreshed: the app shows an equalizer representing the mix of genres/styles played in that moment and the inferred people aggregated mood. The world aggregated mood is computed using the last 100 tweets and assuming that people play a more lively song when they are in a good mood and it's calculated using the acoustic features of the tracks; in particular we used the valence, a measure of the musical positiveness conveyed by a track, provided by the Spotify API.
For the continent mood, we used the last 1k tweets for each continent.


Eugenio Tacchini
back-end & algorithms
Simone Magnaschi
front-end & UX Design
Twitter Logo
We have used the Twitter Api to retrieve the Tweets having hashtag #nowplaying
Spotify Logo
We have used the Spotify Api to compute the valence of a track, to search the top song of an artist and to stream a 30 seconds preview of a song
LastFm logo
We have used the Last.FM Api to get the tags related to an artist
Mentor.FM logo
We have used the Mentor.FM Private API to compute artist similarities.
The logo is a work derived from a picture provided by NASA

The original idea behind this project is an hack developed at the Music Hack Day Berlin (October 14-15, 2016) by Eugenio Tacchini; the hack has been awarded with the Spotify prize and the Universal Music Group Prize.

The original hack can be found here and made use of the Universal Music Group APIs to compute artist similarities. The Universal Music Group APIs have been available only during the hackathon, so for this feature we currently use the private API provided by the recommendation radio Mentor.FM.



Back to top