The Man Who Classified Music

Meet the man classifying every genre of music on Spotify — all 1,387 of them

Do you prefer ‘neurostep’ or ‘vapor house’? Spotify’s ‘data alchemist’ is using technology to help identify new musical trends.

Songs are analyzed by Spotify’s music-intelligence division for a number of factors including tempo, acoustic-ness, energy, danceability, strength of the beat and emotional tone.

(Headline and photo from The Toronto Star, Jan. 14, 2016)

If Paul Otlet was “the man who classified everything”, Glenn McDonald may be “the man who classified everything in music”. The article I’ve linked to here describes a fascinating effort (by digital music service Spotify) to re-classify all of world music, in a way that’s scientifically based. In Spotify’s virtual musical Mundaneum, computers use algorithms to “listen” to international tracks to identify similarities and differences, and then categorize the songs. Afterwards, Spotify’s human “data alchemist”–McDonald–researches and provides descriptors for each new subcategory. So far, over 60 million songs have been analyzed.

The result is an unusually minute and objective picture of world music (see everynoise.com for McDonald’s highly addictive interactive map). In this tag cloud,  “Nordic house” shares weird similarities with “Italian disco”, “Australian dance” and McDonald’s own category, “deep filthstep”—a collocation which a purely human listener might not have been able to pin down.

(Photo of everynoise.com/Toronto Star)

Just another top-down taxonomy with non-hierarchical keywords? Maybe. Either way, McDonald has found an appealing and imaginative way to classify some of world music’s less-known “fusion” sounds, which might otherwise have fallen into “the space between genres”.

Posted by Rose Kernochan, LIS 653-01

Tagged with: , , , ,
Posted in Classification, Knowledge Structures

by Hugh McLeod

Follow INFO 653 Knowledge Organization on WordPress.com
Pratt Institute School of Information
%d bloggers like this: