Slashdot Mirror
Going Head To Head With Genius On Playlists
brownerthanu writes "Engineers at the University of California, San Diego are developing a system to include an ignored sector of music, dubbed the 'long tail,' in music recommendations. It's well known that radio suffers from a popularity bias, where the most popular songs receive an inordinate amount of exposure. In Apple's music recommender system, iTunes' Genius, this bias is magnified. An underground artist will never be recommended in a playlist due to insufficient data. It's an artifact of the popular collaborative filtering recommender algorithm, which Genius is based on. In order to establish a more holistic model of the music world, Luke Barrington and researchers at the Computer Audition Laboratory have created a machine learning system which classifies songs in an automated, Pandora-like, fashion. Instead of using humans to explicitly categorize individual songs, they capture the wisdom of the crowds via a Facebook game, Herd It, and use the data to train statistical models. The machine can then 'listen to,' describe and recommend any song, popular or not. As more people play the game, the machines get smarter. Their experiments show that automatic recommendations work at least as well as Genius for recommending undiscovered music."
I love music, but, alas...I'm getting older, and am stuck in classic rock. Funny...they weren't classic when I started listening to them..haha.
But seriously, even I'm getting a little weary of listening only to the Stones, Zeppelin, etc over and over and over again...
I really love any kind of good guitar driven, bluesy, riff-laden rock. Guitar blues...etc.
I have to guess even in this modern, splintered genre world, there is still some of this type of music being put out by new kids. I've found Wolfmother, and really like that...but, that was a recommendation I got from a friend, but, I don't have the time to find music out there.
When I grew up...it came through the radio. Music wasn't nearly as splintered and specialized as it is today. On my 'rock' stations, I heard Stones, Zeppelin, AC/DC, Steely Dan, Fleetwood Mac, Kansas, Beatles...hell even older than that you'd even hear an occasional John Denver or Olivia Newton John song....quite a mix without turning the dial.
Today on the radio, you have to tune stations all over to get each type of music it seems...and I just can't seem to find something with enough mix to keep my interest. And hit radio...same shit all the time, no variation.
People suggest the internet...well, most of my time is at work, and most places i work..won't allow you to stream music from the web, it is blocked. So, that's not my option.
I've recently discovered Pandora on the iPhone...I have started finding things like that I like from that.
I guess, more things like this and the tech mentioned in the article would really be a blessing for me if I could throw that one while at work, but, would have to be through the phone I guess since no streaming on work computer.
Light travels faster than sound. This is why some people appear bright until you hear them speak.........
It's exactly algorithms like the one used by Pandora that make me agree with the viewpoint that it's not possibly to calculate what "other music" I like based upon the "known music" that I like.
Anyone with a preference for Electro Pop will likely have been wondering when the hell Pandora would learn the difference between Miss Kittin and Scooter after mindlessly clicking "Dislike" on eurodance tracks when Pandora fails to see the difference between one type of electronic music with a repetitive beat and another.
The only really worthful algorithm we'll ever manage to produce is one that uses the collective intelligence of all its users.
Stop being arithmetic supergeeks wanting to put everything inside a box, and start figuring out how to get all these weird unpredictable people to input valuable data into your system.
Google figured this out more than a decade ago, so why are we still seeing stupid mathematical and "pattern-based" algorithms every year?
Setting aside the obvious joke, the "wisdom of crowds" has actually been proven to be useful in certain situations.
If you ask, say, a single person how many jelly beans are in a jar, he may or may not come close. If you ask several hundred people how many are in a given jar and then average their responses, the result tends to be surprisingly accurate.
The problem is that this is limited to situations requiring little to no topic-specific knowledge. Asking a large crowd of random people what the GDP of China is will be a waste of time. It's a technique that requires you to be asking the right questions.
Last.fm's "neighbor" system works similarly, except it looks at what each person listens to. Keep in mind that it takes a fair bit of training to find neighbors who are actually close to your likes, but once you've listened to enough music, it's pretty good at finding things I like but have never heard of. I.E. if I like song A B C and D, and you like song A, B and C, you might like song D.
The neighbor system groups people with similar musical tastes, and allows each person to tune to his/her "Neighbor Radio", to listen to songs liked by your neighbors.
(Disclaimer: I have no vested interest in last.fm besides being a paid member. [My Profile])
I've found a lot of songs/bands I had never heard of thanks to Pandora. I started a station based on "Panic Attack" by Dream Theater, and it's interesting to look at "why was this song selected" for new songs. The current song I'm listening to says "we're playing this track because it features a subtle use of paired vocal harmony, varying tempo and time signatures, chromatic harmonic structure and demanding instrumental part writing." I could have said that I like varying tempo and time signatures, and demanding instrumental parts, but it's neat that it can pick up on things like chromatic harmonic structure and paired vocal harmony.