On music recommendation.

by Dan Bruno

Audioscrobbler is one of my favorite websites. It keeps track of what you listen to via a plugin for your MP3 player and recommends other artists that people with similar music tastes like. Apparently that model isn’t good enough, though — two projects are trying to automate the process of music recommendations.

The first project is called the Music Genome:

Each song has been coded according to a proprietary list of 400 music attributes. Some, like “rhythm” and “tempo,” are obvious to the lay listener; others, like “degree of chromatic harmony,” are more complex, and, well, pretty much require a degree in music theory to explain. The point of all this fuss is to produce the ultimate music recommendation system, a system that’s not based on the flimsy criteria that people normally use—popularity, genre, hipness, how the lead singer looks in tight jeans—but on precisely defined musical characteristics.

The article goes on to say that Music Genome’s goal is really just record sales, but it’s still pretty neat. Apparently its results have been accurate too — a little too accurate, since it recommends very similar artists and rarely strays outside of a given genre. Slate concludes that the Music Genome “is more likely deepen people’s tastes than broaden them.”

The other project is called the Global Jukebox. This one sounds a lot cooler to me:

Interacting with the Jukebox is like having a sophisticated conversation about music with someone much smarter and more cultured than yourself. The simplest way to use it is to pull up a map of the world, zoom in on particular regions and cultures, and listen to music clips. But Lomax wanted people to participate in the process of comparison and discovery as well. To that end, the Jukebox lets you compare and relate individual songs or entire musical cultures and trace traits across the globe. Even more interesting is a function that lets you compare song structure with social structure.

The Global Jukebox has less practical but more exciting conclusions: “a high-energy vocal style correlates with the presence of dairy in a society’s diet; a high degree of rhythmic blending between vocalists signals a high degree of social solidarity; short sung phrases indicate strict disciplining of children; melodic variation is evidence of metallurgy in a culture; and a narrow vocal range suggests rigid rules about female premarital sex.” The skeptic in me dismisses these claims as coincidence, but they’re so damn cool that I want them to be true regardless.