#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.