From The Echo Nest Blog.
The folks at MIT Media Lab, NYU, and Peer 2 Peer University recently set out to teach the world how to manipulate music with a computer and a browser through interactive classes on PlayWithYourMusic.org. When 5,282 people registered for the course, their suspicion that people would be interested in this were confirmed. Then, they had a new problem: how to split all of these people into groups, so that the people in each group would be into the same kinds of music.
After all, one person’s beautiful bebop is another’s frantic nightmare, some people simply cannot abide reggae, and so on.
Before learning how to produce music together, these students first had to get along as music fans.
"We wanted to put them in groups based on their musical taste hoping to improve group cohesion and collaboration," writes P2P U. “We decided to use The Echo Nest since they have an API that helps with doing just that! The Echo Nest provides Taste Profiles – a collection of songs or artists representing a user’s musical preference. The Echo Nest can then relate one taste profile to another – higher scores mean that taste profiles are more alike.”
Their full report is worth a read for a few reasons:
P2P U, MIT Media Lab, and the NYU Steinhardt faculty members behind PlayWithYourMusic.org found that using grouping people by Taste Profile had a positive side effect: “The idea of being grouped this way appealed to many learners who signed up, and they awaited being assigned to a group with much anticipation. This in turn resulted in higher engagements by the learners around musical interest.”
We appreciate a good case study as much as the next people; it’s always interesting to see what happens when the stuff we build gets used in the real world. The problem of splitting thousands of people into hundred groups based on musical taste is an interesting one, and widely applicable beyond the realm of music education.
PlayWithYourMusic is currently accepting students for its next session.