Going Head To Head With Genius On Playlists 174
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."
So, not at all? (Score:5, Informative)
So, not really so much at all...?
Re:So, not at all? (Score:2)
Sponsored herd-it advertisment? (Score:2)
The article links to apps.facebook.com/herd-it/?refcode=slashdot
So I'm thinking this is payed advertisement disguised as an article. That's just low.
Re:Sponsored herd-it advertisment? (Score:5, Insightful)
Re:Sponsored herd-it advertisment? (Score:2)
Yup. This way the folks who created the app can find the most effective place to put their free advertising-disguised-as-news.
Re:Sponsored herd-it advertisment? (Score:2, Interesting)
Re:Sponsored herd-it advertisment? (Score:2)
If submitter registered slashdot, and is getting some kind of benefit from it, that's in poor taste. Boo!
If slashdot registered slashdot, and is getting some kind of benefit from it, that's also in bad taste. But whatever, we expect that from slashdot
Bias exists for a reason (Score:2, Interesting)
When are people going to realize that unpopular music is unpopular for a reason. Sure the music execs try to push their own artists more than others, and they try to target the largest cross section of the population as possible, but why wouldn't they?
Trying to bring 'unpopular' must to the masses because that will suddenly make it popular is stupid. Music becomes popular because someone hears it and likes it, not just because they hear it.
Throwing Timmy's garage band onto every radio station in the world during prime time isn't going to change the fact that Timmy's garage band sucks and very few people want to hear it.
Yes, there are people who don't have the same tastes as the general public, that is a small portion of the public, nothing you do is going to change that. There will always be a bell curve. Stop with this crap of think just because you like some indie band that no one has heard of that everyone else will.
If the general public likes them they will become popular. If they play a local show and people like to hear them, they'll get requested and more people will hear them. Then more places will request them, and rinse, repeat, until they will become popular.
Unknown bands are unknown because they are interesting or 'good' to a small number of people, not because of some silly idea that they got shafted by a playlist generator. The playlist generator is simply following trends that it learns from people. It doesn't actually analyze the music to find the algorithm that makes it 'good music'. It says 'People that listen to this song also like this song, add it to the list', rinse, repeat, playlist generated. It doesn't say 'hey, no one listens to this song, lets throw it in and then everyone will like it!!!
Re:Bias exists for a reason (Score:2)
Re:Bias exists for a reason (Score:5, Insightful)
Are you generally this obtuse?
The idea is not to popularize shitty bands. Given perfect AI, this program is supposed to do the following:
1) Listen to all popular music (for various classes of popular).
2) Figure out why that music is popular (for its class).
3) Listen to any *new* track and figure out if it is like those popular tracks (and any popular class).
Now of course we don't have that kind of AI and hence all this research.
The idea is to promote good bands that would have been popular except for the fact that they are not already popular and hence might go unnoticed.
Re:Bias exists for a reason (Score:2)
But what if you like to discover *new* music and not music that is like the other music you like? I mean, before the crackdown on webradio there were gazillions of (private, run by an individual or small group) stations and when I tried a new station and liked the first two or three tracks I heard (did not happen that often) I could rely on the fact that I would like many of the tracks that got played there. Even if I hardly knew any of them and even if they were extremely different. There's more to musical likes and dislikes than statistics and AIs can unearth.
Re:Bias exists for a reason (Score:3, Insightful)
3) Listen to any *new* track and figure out if it is like those popular tracks.
The idea is to promote good bands that would have been popular except for the fact that they are not already popular and hence might go unnoticed.
In this scheme, the no-name band that is most successful in cloning the big-band sound will score the highest.
You might as well be hosting the Fat Elvis competition at the state fair grounds.
Re:Bias exists for a reason (Score:2)
In this scheme, the no-name band that is most successful in cloning the big-band sound will score the highest.
Which gaming of the system is trivially defeatable via a cut for bands that are clearly clones of existing big-name bands. If some random /. reader can spot the issue--and it will only be an issue with a system that can actually measure similarity accurately--then you can be pretty sure the researchers working on this stuff will spot it as well.
Since, by hypothesis, they have a system that can accurately measure similarity it becomes tivial to eliminate bands that are too similar, and therefore clones.
Re:Bias exists for a reason (Score:2)
Re:Bias exists for a reason (Score:2)
If they play a local show and people like to hear them, they'll get requested and more people will hear them.
That's seriously how you think it works? People just get gig after gig and work their way up and eventually [major label] just starts throwing money and contracts at them?
Where you live, who you know, and how much free time and money you have matters a _lot_ more than how good you are. Sure, talent can eventually get you there too, but for most bands it doesn't. Your options are either to have some contacts that can get you in front of someone important quickly, or to have a shitload of money so you can do nothing but tour for a while. Because even a really good band will likely take a couple years to start getting enough money to live off of from their music - if they ever do.
Besides, record labels aren't interested in signing good bands, and they aren't interested in signing lots of bands. They're interested in signing as few bands as possible while pushing out as many of those records as possible. And they'll spend billions of dollars getting airtime and advertising to do that. Popular music is not what people like, popular music is what the record companies pay to have on every radio station, in every movie and TV show, every commercial...everywhere. I can't remember the last time I actually listened to music on the radio - or met anyone else who did. Yet somehow that still defines what is popular.
Re:Bias exists for a reason (Score:2)
You do realize that movies & TV shows have to pay to *use* music, right? I realize that nowadays, with 'linked' TV/music production houses, the opposite is likely happening too. (e.g. the "For more info on the music played on this week's show" at the end.)
Also, they can't legally pay for music to play on radio stations. http://en.wikipedia.org/wiki/Payola [wikipedia.org]
Re:Bias exists for a reason (Score:2)
Yes, I realize both of those. But it still costs money to get music to movies, TV, and radio. Advertising. Promotional material. Sure, they're not directly paying radio stations to play their music, but sending a CD out to every radio station in the country isn't exactly cheap. Sure, a small indie band could maybe get some local college stations to play their stuff, but they don't have near the weight that a big name studio has.
Re:Bias exists for a reason (Score:2)
Re:I'll tell you how. (Score:2)
I've never heard Kings of Leon so I can't say if they "deserve" to be popular but I will say this, there have been countless examples of bands/musicians who have produced pretty good music, music which has some artistic merit and a small but loyal following, for a long time and then one day they release an album or a single where they simply mix their sound with whatever is popular at the time and all of a sudden they become popular, their original fans and other fans of the genre reject them and they go on to make big bucks before fading into obscurity because they couldn't keep up with the constant changing whims of the mass market. Does this mean the band's music was bad to begin with? Or does it simply mean that there is at any given time certain sounds and styles which are trendy and if someone chooses to latch onto one of these trends and has some basic talent one is able to become rich and famous (until the a new trend comes along)?
/Mikael
Re:Bias exists for a reason (Score:2)
Throwing Timmy's garage band
Timmay, timmay timmay TIMMAY TIMMAY timmay.
Timamy,
Timmay.
Re:Bias exists for a reason (Score:3)
While I have no doubt a computer program could figure out that I like certain tempos and time signatures and musical patterns, none of it says whether it is any good.
What I don't understand is the concept that it has to be 'fair'. There are thousands of wonderful singers, songwriters, musicians,and drummers out there. I can listen all day to great music, who cares if some unknown in Gary Indiana is better and is being ignored. Tell him to get off his fat ass and work to get noticed like everyone else has had to. Times are changing, and myspace, facebook. blogs in general, and other Internet features make it simple to get your work out there and link to albums on Amazon if someone wants to buy it. Tell these kids to stop whining because no one knows about it. As the parent said, if it is any good
If these kids would stop listening to their mother and boyfriend/girlfriend's opinions, maybe reality would set in and they would find out they are just as mediocre as everyone else is.
Kids these days
Re:Bias exists for a reason (Score:2)
Stuff they say won't becomes stuff like Peaches... Rush... the list goes on :)
Just because some industry scount likes a band and dislikes another doesn't automatically mean one sucks and one rocks. I'd point to the popularity of the Jonas brothers as a good example.
A lot of what the record industry offers is EXCELLENT studio processing. The difference between a great song and a merely good song is sometimes just the production values. Go watch some concerts, really. Some of the top bands sound like complete ass when they are not set up properly (and some just cheat and play pre-recorded versions)
Anyone actually use "Genius"? (Score:4, Insightful)
I tried Genius for awhile, but I recently disabled it for two reasons:
1) The "recommendations" were not very good nor did they maintain a "common theme", by which I mean, I chose a rather edgy electronica/punk song by Crystal Castles... three songs down we get something by The Nationals... which is very mellow rock. If I choose a song that is edgy, electric, and with a faster pace, I want ALL the songs in that 25 song playlist to be at least within a similar genre.
2) It takes up too much time when importing vast libraries to new machines. I recently centralized my 300+ GB music library on a Mac Mini Server, iTunes was unusable due to genius choking on the sheer volume of data it had to deal with.
In the end, it's really nothing more than a way for Apple to try to get you to buy more crap from the Apple store.
They lost my wallet years ago to Amazon MP3 store who had no DRM. I see no reason to go back to iTMS even now that their DRM is gone. Especially seeing what dicks Apple has been with their conduct around ACC, "fair play", and App Store lock-down.
Re:Anyone actually use "Genius"? (Score:3, Insightful)
I've made three observations with Genius:
1) It used to be much, much better. Whatever Apple's doing to incorporate new data is having an adverse effect on the quality of the results.
2) It doesn't work particularly well with large libraries. When I upgraded my hard drive, and merged my "archival" collection with the "everyday" music I carry around with me, I found that the quality of the genius results seems to have deteriorated, even though it doesn't necessarily choose any songs from the huge pile of jazz and classical that I added.
3) Genius seems to ignore album tags. If I have two copies of the same song (as happens sometimes, as I like collecting live recordings and radio sessions), Genius seems to pick whichever song is alphabetically first. This can be annoying, as it prevents certain songs from *ever* appearing.
Re:Anyone actually use "Genius"? (Score:2, Informative)
The biggest problem is that Apple is probably the closest internet-based distribution system to the record labels of old. Perhaps this is an "appeal to the masses" approach or to get onside with the labels.
The downside of this is that a collaborative filter based on genre and sales will never go deep. I doubt they'd ever use pearson's correlation coefficient seriously enough to offset the "this is the new hit everyone listens to so you should too".
I guess it comes down to musical integrity to the extent of ignoring trends to deliver truly accurate results... or hit 90% of the market with a simple solution that probably makes them more money and makes the record labels easier to deal with.
Glad to see they're thinking different and aren't just playing to the status quo.
Re:Anyone actually use "Genius"? (Score:2, Interesting)
Well, actually, yes. I use Genius. A lot.
Look, it's not perfect, but for folks like me, who don't have either the time or the desire to craft a playlist for each mood I may happen to be in, it's a godsend. Before Genius came along, my options were either to listen to a specific album or artist, or shuffle the whole damn iPod. I'd do that occasionally, but the end result was heavy on Beatles and J-Pop. I obvious like both genres, or my iPod wouldn't be full of the stuff, but sometimes I'm just not in the mood for either. The Genius playlists do a decent job of segregating my collection into various flavors of rock, J-Pop, and anime soundtracks.
It's just a matter of convenience for this casual listener. I can understand why a more hardcore music collector (like say, someone who has 300+GB of music) might not find Genius sufficient. But then, I find it hard to believe such a collector would be satisfied with any automated playlist generator.
------RM
Re:Anyone actually use "Genius"? (Score:2)
Funny but I've usually been quite pleased with the Genious selection. I'm more inclined to try Genious just because it makes it easier to put a list together. I can always manually 'improve' the list if a few songs don't fit. I'm not expecting perfection and neither should you. Although it would be interesting to see more obscure songs be suggested. Algorithms have to be based on something and that something contains some level of bias.
for some, 'good' and 'popular' are the same (Score:4, Insightful)
Just tried this out (Score:2)
The first track that played was a System of a Down tune. Which is about as pop as it gets. The ones after didn't get much better. If they really want to use this to push less played songs which have potential, they should actually better get some.
The Academic meets Capitalism (Score:4, Insightful)
Capitalism: Hello there Academic. How are you?
Academic: Hi... what they heck are you? You look so strange to me...
Capitalism: I'm Capitalism. Oh, I'm really not all that strange, but I might be a little complicated to understand.
Academic: Complicated!?! I am the master of complicated, I am an Academic for crying out loud.
Capitalism: Ok then. Let me try to explain myself. I am a system that provides stuff via supply and demand.
Academic: Nonsense! I dont hear music that deserves to be heard on the radio or on popular websites!
Capitalism: Deciding who deserves what really isnt my thing... see... its about supply and demand...
Academic: But who decides whats in demand!?! Certainly it cannot be the uneducated "masses", they... just aren't qualified!
Capitalism: No no... its about what many individuals, smart or otherwise, want based on need or dozens of different other factors.
Academic: Preposterous! How could they possibly know what they want or need if they havent been exposed to it?!? Foolish Capitalism!
Capitalism: Well, there are a lot of musicians out there and only so many different ways to get them heard, and, well, there are people out there who spend their lives learning what people like and dislike, and even they arent always right... so the best at determining who does best succeeds...
Academic: Rubbish! What we really need, is for the qualified, with a broad base of tastes to make an application for people to give them a view of all the music that is out there!
Capitalism: I guess you can try, no one can stop you, but you might not succeed.
Academic: Your so short sighted. I don't need to worry about succeeding, I receive public money to pursue my higher realm of thinking.
Capitalism: Right on... so I guess you will compete and regardless if your product sucks, you dont have to worry about it because your really just spending someone elses money.
Academic: Its progress my dear boy. Progress.
Someone else's money (Score:2)
if your product sucks, you dont have to worry about it because your really just spending someone elses money.
Pretty much the story of most equity-funded businesses (particularly venture-funded.
And C-level agents.
Re:Someone else's money (Score:2)
They love big unaccountable government.
And have the higher standard of living to prove it.
Re:Someone else's money (Score:2)
See, difference between taxes and equity venture-funded capitalism, is...
You can safely spare me the obvious points. I'm keenly aware of the underlying differences in the fundraising mechanisms, in how competition operates within both worlds, in the different investment vehicles, and in where the yields go. Just pointing out one similarity (among a number) that appears to be non-obvious.
Of course, seeing your signature, its obvious that you dislike competition and pray at the alter of big, all powerful government.
You're quite wrong. The only thing you should conclude from my sig is that the consternation among movement conservatives over TFD is one of the pieces of evidence that the conventional wisdom they're underdogs in broadcast media is false.
Not only do I have a considerable amount of theoretical respect for private enterprise and markets as mediating social institutions, I like participating: I've spent the better part of my career working startups and hanging out my own shingle.
But I definitely take exception at unsubtle analyses and digs at other social institutions, including those apparent in the GP. The fact is that academic institutions have to compete for funds, that individuals who participate in it have to compete with each other for project and research funding as well, that there are real incentives even beyond this competition to produce good and useful work, and that these institutions yield dividends to the communities that sponsor them. And that the real business world is full of people who aren't concerned about whether they're using other people's money effectively [wikipedia.org].
Does that mean that private enterprise sucks and academia is better? Hardly (leaving aside the fact that the question presents a false dichotomy). No single tool, however versatile, is the right one for *every* job.
Perhaps you should move to Europe. They love big unaccountable government.
I expect it would be pleasant. Many if not most European states arguably have economic freedom and prosperity that equal or rival ours, interesting cultural heritages, function as representative democracies (what was that about unaccountability?), and have their own opportunities for entrepreneurs who can find the right space. But I enjoy it here in the US as well, and care about it too much to leave it to people who don't seem to have more than a single idea about what makes a successful and prosperous society.
Re:The Academic meets Capitalism (Score:3, Insightful)
Re:The Academic meets Capitalism (Score:2)
Re:The Academic meets Capitalism (Score:2)
Interesting theory, but I'd pay for a system that introduces me to songs I haven't heard before that I might like. I don't care if it's popular (or good) if I like it, I like it. For instance, this [google.com] is in my "a" playlist at the moment. Right next to "Waking up in Vegas" which was a top 40 hit not too long ago.
Such a service actually fits within capitalism, if enough people are interested. I have to agree that Genius just doesn't seem to do that for me.
Re:The Academic meets Capitalism (Score:2)
You make a compelling argument Mr. Capitalism,
I'd just like to say;
Pat Boone
Grateful Dead (I think their following enjoys the flashbacks, and so the love of their music is more of a trigger -- if you never got stoned to the Grateful Dead, then you probably don't get the attraction to this elevator music).
Jimmy Buffet (yes, I said it. God save us all from the popularity of Margarittaville and listening to another aging drunk doing his white man's overbite to this moldy oldy).
>> And even more, economic go-to people who bring in the bucks:
Dane Cook
Blue Collar Comedy Tour,
Gallagher,
Carrot Top
>> I think I'm going to try out this heuristic algorithm that the Academics dream up. They aren't grading it on correct use of English, after all.
Re:The Academic meets Capitalism (Score:2)
Academics drive Capitalism. High-level research is not done by corporations (anymore--there used to be places like HP that did, but Carly, being an ignorant capitalist, killed that off). Publicly-funded research is what hands ideas to the private sector. Sometimes academic research just breaks off and becomes private (Google).
The point of making products/ideas without competitive accountability is to explore the possibilities that lie beyond what pays out in the short term. The slow death of American academia is ultimately what is going to kill off the economy as well. It just takes time for the consequences to trickle into the private sector.
Nothing worthwhile, nothing, from the last century, was made by the private sector alone. Nothing. I don't care what technological innovation you think of; if we dig back through the history of that thing, we're going to find taxpayer-funded academic research.
I don't want to live in your ideal society, and I don't actually think you would like it, either. The last time we tried it your way, it was affectionately known as the Dark Ages. You may think you'd be a knight or a nobleman, but I think it's a lot more likely that you, me, and everyone we know, would be serfs.
Re:The Academic meets Capitalism (Score:2)
KKline, you must be an academic... I can tell by your sense of humor and your sense of irony.
The post is not saying academics dont contribute.... Its the shmarmy belief that they "know better than everyone else", even when it comes to things that are subjective (which is really a large part of the free market). The Academic fantasizes about the Technocrat that will eventually lead us all into utopia by prescribing us "plebes" the perfect formula to live our lives, which of course, has lead to the greatest calamities in human history (see China, Russia, and a slew of other communist experiments in the 20th century).
You say I'd lead us into the dark ages, but I say you would lead us into the Gulags of Siberia.
Re:The Academic meets Capitalism (Score:3, Informative)
The Academic fantasizes about the Technocrat that will eventually lead us all into utopia by prescribing us "plebes" the perfect formula to live our lives
For example, the Chicago or Austrian Schools of Economics.
Engineers at the University of California vs. Me (Score:2)
I wrote something earlier this week to do the same thing with the hashtags in the Twitter API and my music DB.
If you're bored, check it out. The recommendations are pretty close (bottom left). Metallica [clinko.com] or Weezer [clinko.com]
I found this one interesting Beatles [clinko.com] because it finds the singers names.
People like what other people like (Score:3, Informative)
For possibly the great majority of the population, music can be compared to fashion; does not really matter if the art is good per se, what matters is the trend and popularity, on a local scale (what my friends listen to) and global scale (media).
With the rock'n'roll revolution in the fifties, lots of teenagers liked that new music in part because it wasn't their parents' music. Same story can be said of disco, rap and grunge.
Problem with the long-tail approach is that people mostly judge music by non-musical criteria.
Last.fm (Score:5, Interesting)
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] [www.last.fm])
Mod parent up (Score:2)
The neighbor playlist on last.fm is a really effective tool for finding stuff I didn't know about but like.
Re:Last.fm (Score:2)
Well somehow I feel that I must be an oddball in the specificity of my tastes, but while my best neighbours listen to a lot of things that I also listen to, the rest of what they listen to I already know and dislike. So in my case it's like the neighbour system can only identify the overlap, but can't find anyone who listens to things I may like but don't know yet. Although I suspect that due to the specificity of my tastes, there's perhaps no such thing as someone who likes what I like and likes what I will like. I can't even find anyone who likes the two main genres of music I like at the same time!
Likewise, most of the suggestions I get are for things I already know but don't like. I think the thing is that it assumes that if you like something in a genre then you'll like mostly anything in the close vicinity, whereas in my case while what I like fits in relatively small areas, what I dislike shares the same area. So it keeps suggesting me things in that same area not knowing I already dislike that. Not only that but since that's a fairly small area I know pretty much all that's worthy of being known there already and could use some suggestions as to what explore next that is in a neighbouring area.
This being said, an artist's neighbours is much better defined, but you'd expect that to be more straightforward to determine and reliable.
At least as well (Score:2, Insightful)
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.
Their experiments show that automatic recommendations work at least as well as Genius for recommending undiscovered music.
At least as well as never recommending? That is astounding.
High Fidelity (Score:3, Funny)
Paraphrased from actual conversation in an indie record store:
Record store owner: "Why do people keep coming back here?"
Employee: "Well, it's not friendliness..."
Owner: "WHAT?! I'm the most f***ing friendly guy there is!
Genius doesn't work for me (Score:2)
I disabled Genius and just leave it on Random play. I have 35,654 songs, so I basically listen to the best radio station and rarely hear repeated.
Heck, if I live to be 90, I'll probably only hear each song 7 or 8 more times anyway...
Genius doesn't work for me either (Score:2)
Re:Genius doesn't work for me either (Score:2)
Genius is a relative term. Consider the average Mac user and well .... I KEED, I KEED.
Doesn't work for me (Score:3, Insightful)
I've played with Pandora radio a bit before, but it doesn't tend to work for my taste in music. I like songs with funny lyrics... Monty Python, King Missile, Nellie McKay... the algorithms that focus strictly on musical styles generate pretty hilarious results, but not what I'm looking for :P
I've been pretty happy with some of the dj internet radio stations, though, like somafm.com and some of the ones on di.fm . Before I found some of those stations, I didn't really think there was much of any music that I liked. Certainly not on broadcast or satellite radio.
Let me get this straight... (Score:2)
They're using people who play Facebook games to train their systems to be smarter?
The mind wobbles.
Meaningful data first play, bs on repeats (Score:2, Insightful)
Re:Wow. (Score:3, Interesting)
There, now we got that out of the way (and I do feel oddly better about life) I have to say that I'm still skeptical about these algorithms for music recommendation.
A friend of mine and I listen to a lot of the same music. He got me on the soul train in a way, so we talk a lot about Soul, R&B (The old fashioned kind), Funk, Rare Groove, Jazz and Gospel. Now he and I can dig the same song for wildly different reasons. We can sit and discuss the same tune, which we both like, and discover we look at the thing so differently it's as though we're from different planets.
Now I've tried all possible music sites and playlist generators, but at the end of the day I simply never really agree with the correlation they see between song one and song two. I really wonder if the /. audience believes something as complex as music appreciation can be captured in a program....
Re:Wow. (Score:5, Insightful)
I know you say you've tried all possible music sites... but on Pandora if you create a new station from an artist or song, they'll give you the criteria they use to populate the playlist.
Set up stations based on enough songs, and it's pretty easy to understand at least part of how their algorithm works. A big problem, of course, is that some of the criteria are somewhat subjective, which is why you may disagree with them. I find this especially true when creating stations based on artists, not songs.
I just wish I could tweak the individual conditions to see where it'd get me... like having all criteria match except genre.
Mathematics != human preference (Score:5, Interesting)
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?
Re:Mathematics != human preference (Score:5, Funny)
If your algorithm don't got Mojo Nixon, then your algorithm can use some fixin'.
Re:Mathematics != human preference (Score:5, Insightful)
But that's not the point of the algorithm. The point is to generate a playlist of songs that share some characteristics with criteria you have specified via examples (seeds for a station, and up/down votes on songs in the playlist). It's not about your personal likes and dislikes, it;s about songs that are similar.
My personal experience: Don't use downvotes until the station is somewhat mature. Use upvotes only, so the algorithm can find the common ground basis for the station. Then, after 10-20 hours of playtime, use downvotes to start eliminating unwanted characteristics.
One last point: Pandora is good for general tastes. As your wants get very specific within a genre, as you point out, it starts to fail. My general advice for you is to not try to use Pandora to create a pseudo-random playlist of only songs you know you like. After tailoring your station, buy the songs you like. Then you can create a playlist in your preferred audio-file management software, and listen to only the songs you like. Revisit Pandora or elsewhere to expand your collection as needed. I think this is the only way you'll be really satisified.
Re:Mathematics != human preference (Score:4, Insightful)
It's nice to be important but it's more impo...etc (Score:3, Insightful)
Please read the GP. He's talking about the difference between Miss Kittin and Scooter. Scooter! There's a difference between "broadening your taste" and licking out a septic tank.
Re:Mathematics != human preference (Score:2, Informative)
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?
The neural network is trained on crowd-sourced data. TRANSLATION: These supergeeks actually DID figure out how to get all these weird unpredictable people to input valuable data into their system. The solution they designed is that people will play their Facebook game, herdit.org, and the statistically significant answers to the quiz game are tagged to the song clips. These tagged song clips are then used as a training data set for the neural network. The machine algorithm is a result of the collective intelligence of all the players of herdit.org
Perfect, no.. (Score:2)
As someone who listens to a somewhat eclectic assortment of dubstep/industrial/electronica with smatterings of indie/electronic pop I do find new music from the suggestions (I'm probably my own best user). I can't speak to pandora because I never really started using them, but if you can't find new music using last.fm you're probably losing patience with it.
Naturally if you end up creating something that provides even better artist recommendations I'll be glad to use it too.
Re:Mathematics != human preference (Score:2)
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.
I've been wondering about that for a while. That Pandora actually sees any difference at all in some cases shows that it's already a pretty amazing tool.
ob xkcd [xkcd.com]
Re:Wow. (Score:3, Interesting)
I just wish I could tweak the individual conditions to see where it'd get me... like having all criteria match except genre.
Even a line-item veto for the "why did you play this song" would be ideal. Thumbs up or thumbs down on every song seems to make the music selections worse, not better. Obviously which songs I like and which ones I don't doesn't neatly boil down to criteria that pandora can identify, so I think it's unavoidable that it will pick up on what it thinks I like but I don't.
For example, I like hip hop with clever lyrics, but hate rappers who can only talk about themselves. Most hip hop artists though rap about themselves at least a little, even the ones I enjoy. Simply because all rappers rap about themselves at least a little, any song I give a thumbs up, it's always going to think I like that and will start playing songs that are -only- about the rapper. If I make a station around Aesop Rock, who rap about things besides how well they rap, the selections are good. If I hit "I like" for too many songs though, the selections get worse, looking in "why did you play this song" there is always a line about "boastful lyrics." Being able to select "no, not that one" would be a plus, as the other criteria get better.
(Please, try to resist the temptation to post on how you don't like hip hop. I know, I know, rap music is missing a c, that's very clever.)
Re:Wow. (Score:2, Informative)
I remember reading somewhere in the pandora algorithm that you should only click "Thumbs Up" for songs you really like, not every song you like. If you like a song, but there are aspects of it you don't like then don't select anything, just let it play.
I know this isn't as nice as being able to select individual features of a song, but what are you going to do?
Re:Wow. (Score:2)
I know this isn't as nice as being able to select individual features of a song, but what are you going to do?
Whine on slashdot about a free service that lacks one feature I think would be good.
Oh, that was probably rhetorical...
No, I have heard that, but in the case I said, nearly every hip hop artist can accurately be described as boastful, because they all do. Giving -any- thumbs up seems to strengthen that.
Re:Wow. (Score:5, Interesting)
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.
Re:Wow. (Score:2)
I meant that it picks up that I like that, not that I thought it analyzed the song and determined that.
Re:Wow. (Score:3, Informative)
I've had great success with Gnoosic [gnoosic.com]
Re:Wow. (Score:2)
Re:Wow. (Score:3, Insightful)
I'm still skeptical about these algorithms for music recommendation.
You should be skeptical, but not dismissive. In its current state, this type of service is more like directed browsing than a true recommendation. But it still yields the an occasional gem, and with continued participation and increased competition it will get better. Skepticism makes it a useful tool, if you can live with having to wade through some misses along with the hits. Blind acceptance will, of course, be mercilessly exploited and the unwashed masses will still end up listening to the likes of [insert music you despise].
Re:Wow. (Score:2)
I really wonder if the /. audience believes something as complex as music appreciation can be captured in a program....
It's not like music can be represented mathematically or anything. A computer would never understand that.
Re:Wow. (Score:2)
My taste in music has been described by more than one person as "random," so yeah, I'm with you.
Re:So I guess Skynet's HK's (Score:2, Funny)
HKs will listen to METAL.
Re:It's time to put it to a vote: (Score:2)
It can be used in ironic terms to great effect.
Re:It's time to put it to a vote: (Score:2)
You have to replace it with something.
How about "wisdom of the dumb, panicky, dangerous animals."
Re:It's time to put it to a vote: (Score:2)
When you're talking to dumb, panicky, dangerous animals it's usually best to keep the information flow as uncompressed, redundant and calm as possible.
Re:It's time to put it to a vote: (Score:2)
The "wisdom of the crowds" nor iTunes' Genius wonn't help if you have music that's so unique that it can't be pigeonholed. Think Ska in the 50s, Raggae in the sixties, Rap in the seventies.
None of these genres were anywhere near popular when when they were new in the times listed. Nor were they played on the radio.
I doubt that iTunes Genius will ever serve up The Station to anyone, despite the fact that IINM you can "buy" their stuff from iTunes (or get it free from archive.org) [archive.org]
Re:It's time to put it to a vote: (Score:5, Funny)
The wisdom of the crowds seem to be proving you wrong.
Re:It's time to put it to a vote: (Score:5, Interesting)
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.
Re:It's time to put it to a vote: (Score:2)
And I agree with you. Crowds are a useful for reducing inaccuracies, such as with your jelly bean example. But there are circumstances where the majority of the crowd is biased or uninformed in a systematic fashion... and in that case, a larger sample just gets you a more accurate incorrect answer.
I suspect that crowds might be useful for classifying music, but not really that useful for recommending music. You can pick two fans of a very narrow, specific, musical genre, and they may like entirely different songs from that set.
Re:It's time to put it to a vote: (Score:2)
Well that would explain why FOX News is 3 times and 4 times more-popular than CNN and MSNBC according to Nielsen Ratings.
(Ducks a tomato... or is it to-mat-o?) (To-mate-o, to-mat-o, po-tate-o, po-tat-o - ahhh let's call the whole thing off.) (Yes 1920s culture lives on because it's now public domain. Frak you RIAA.)
Re:It's time to put it to a vote: (Score:2)
For the jelly beans, do they take the arithmetic average or the geometric average? It would be interesting to see which comes closer.
Re:It's time to put it to a vote: (Score:2)
Re:They should go through my collection... (Score:5, Interesting)
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.
Re:They should go through my collection... (Score:2)
Same experience here (except Pandora on the PC, not iPhone).
Best part -- not only am I continually discovering new music, I'm rediscovering classic rock I'd forgotten all about.
Try adding David Grisman to a station you've created based on classic rock. Might not rock out as much as you're used to (almost 100% acoustic, since he's a mandoline player), but the man is a genius. I've gotten into bluegrass (especially "modern" bluegrass like Supergrass from the 80s) because of him... and one of the stations I listen to most on Pandora is Led Zep + David Grisman. Nice variety, and great guitar/mandoline/banjo all around.
Re:They should go through my collection... (Score:2)
Might also try things like Jet, Fratellis, etc. They're pretty decent examples of a modern approach to the 70s rock.
Pandora rocks :)
Only downside - it frequently seems to think that *all* versions of a song are the same, but just because the brand new live version of a Metallica song sucks doesn't mean the older live versions and the studio version suck.
Re:They should go through my collection... (Score:2)
Mind sharing your Pandora UID so I can check them out? (Mine's the same as here... but my station list is currently full of crap as I've been trying to show my wife the possibilities).
Re:They should go through my collection... (Score:2)
... but my station list is currently full of crap as I've been trying to show my wife the possibilities).
Wow, I can sympathize with that! I did the same thing with my Tivo. It used to be great with recommendations for thing's I'd like, until I finally taught the wife how to use it. Now it records reality shows, celebrity news and Tyra Banks reruns. That's a true sign of the apocalypse there - when a great SI swimsuit model has a show and it's the wife who wants to watch it and the man who runs in horror!
Grisman plays... acoustic vegetables? :) (Score:2)
Wow, Grisman would *have* to be a genius to play the mandoline musically, as that's a kitchen gizmo for slicing things [wikipedia.org]. But then I have heard him play the (no "e") mandolin [wikipedia.org], and yes, the man is a genius, or at the very least extremely much more talented than I am. :) Heck, I think there's even an established style of mando playing named after him -- sure enough, his Wiki article [wikipedia.org] makes mention of "Dawg Music".
Whatever he's playing though, it'll probably sound pretty damn good.
Cheers,
Re:They should go through my collection... (Score:2)
Re:They should go through my collection... (Score:2)
My Gripe with Pandora (Score:3, Interesting)
Is to get 10 recommendations I have to listen to 10 songs in a row due to their skip limitations.
They can keep their skip limitation, that's fine, I get the licensing problem they have.
But why can't I get a simple list of the next N (10, 20...100?) songs they'd recommend based on my current "station"? It might even improve their recommendation engine for me because I could thumbs up/down (and I suppose, "I'm tired of this one", too) the songs and cut through the cruft faster. Sort of like Netflix "Rate Movies" engine which allows for more inputs to the rating system.
I also am annoyed that you can add a *song*, which is highly specific, or an artist which is somehwhat specific, but not highly so given some artists creative changes over time, but you cannot add by *album*.
For example, IMNSHO REM's Chronic Town, Murmur & Reckoning are brilliant and most everything else after is less (often much less) so. Adding those *albums* defines a general yet atomic set of musical criteria; adding the entire band and all its albums biases it much more towards the later records, even by sheer weight of number of songs.
This is true for dozens of bands whose sound changed substantially over time or whose last N albums were horseshit or whatever.
All in all, I *want* to like it but the "service" doesn't mesh with how I listen to music from a practicality sense (streaming via iPhone blows on my car stereo and is a battery hog elsewhere) and 10 recommendations aren't worth 30 minutes of sitting down.
Re:My Gripe with Pandora (Score:2)
I don't use Pandora (regularly, I've played with it).. but you can skip 6 songs per hour PER STATION, 12 total per day on the free version.
According to their FAQ, if you pay you get rid of the daily skip limit. I thought I've heard others say that if they hit their limit (e.g. the hourly limit per station), they just change to a different station. I thought I remember some guys on the HD & Home Theatre podcast (who go offtopic sometimes) saying you could create multiple stations with the same criteria, so you can get around the (hourly) skip limit by switching to another identical or similar station -- which would choose different music to start with.
Re:They should go through my collection... (Score:3, Informative)
Well, when possible the internet is the best place; you can get "radio" from just about every radio station in the world. Go to KSHE [kshe95.com] for the oldest FM stereo rock station in the world, [kuro5hin.org] who played "classic rock" before it was classic and still do, along with some of today's dreck. On Sunday night they play seven albums in their entirety, back to back.
College stations are great, too. The one here in Springfiled, WQNA, [slashdot.org] is the only station I've ever heard where you can hear Tennessee Ernie Ford followed by the Dead Kennedies, followed by Johnny Cash (The DKs are a 70s punk band). Sunday mornings is old 30s and 40s jazz, noon is a blues show, Tuesday nights there's a "hardcore" show followed by a country oldies show. Wednesday nights they have belly dancing music, etc.
Re:They should go through my collection... (Score:5, Informative)
Actually I've found last.fm's recommendation system works extremely well; so well in fact that I constantly have a tab open to it when I'm browsing music stores like eMusic (eventually I want to write a little app for this purpose using last.fm's API, but I digress). For those unaware, last.fm users submit what they're listening to through automated plugins (and the supported apps list is huge and very platform independent, I personally use both Amarok 1.4 and MPD); one of the things last.fm does with this music is identifies your "neighbors" (people with similar lastes, i.e. 8 of our top 10 artists are identical). I've found that one of the best ways to find new music is by browsing what my neighbors are listening to and checking out any of their top bands that I'm not familiar with. They also list related artists by correlating this information (e.g. the majority of users who have Band A as a favorite artist also like Band B). Another useful feature is being able to check what an artists most played songs are (great for when it's an artist you never heard of). With that said, I'm definitely interested in seeing what recommendations come from this UCSD team (and not just because I'm an alumnae) as I'm always interested in finding new artists, especially smaller and local ones.
Re:They should go through my collection... (Score:2)
I just gave last.fm a try, and I was unimpressed. It kept picking obscure songs from Lindsay Lohan or Ashley Tisdale. I'd rather keep listening to my local Hot A/C-Urban station.
last.fm on android (Score:3, Interesting)
I don't know how last.fm works but I downloaded the android application on my phone and so far it is treating me well. It is much faster than pandora and allows me to listen either by entering an artist, tag, or user. So in tags if I type in Jpop I get a bunch of japanese pop songs. I can find stuff from other countries as well which is cool.
It almost feels like iPods are overrated now. It would be cool if I just subscribed to a service and used my phone to stream in music based on my preferences or playlist. Then all music available on the internet (world) would be accessible as long as I had a 3G signal.
Re:They should go through my collection... (Score:2)
P.S.
I also enjoy listening to Radio Jackie in London - http://yp.shoutcast.com/sbin/tunein-station.pls?id=225101 [shoutcast.com] (dialup) - http://yp.shoutcast.com/sbin/tunein-station.pls?id=715112 [shoutcast.com] (broadband)
Re:They should go through my collection... (Score:2)
and not just because I'm an alumnae
There's more than one of you?