Feed aggregator

RT @tricil: @threv also, extensionfm!!! I feel like I just discovered winamp or lastfm for the first...

Dan Kantor - AOL Music - Sat, 07/31/2010 - 18:05

RT @tricil: @threv also, extensionfm!!! I feel like I just discovered winamp or lastfm for the first time.

Categories: Music Rec

RT @majman: SoHo seriously needs a combination Pizza Hut & Taco Bell

Dan Kantor - AOL Music - Fri, 07/30/2010 - 19:56

RT @majman: SoHo seriously needs a combination Pizza Hut & Taco Bell

Categories: Music Rec

This is great - http://www.openappmkt.com

Dan Kantor - AOL Music - Fri, 07/30/2010 - 19:56

This is great - http://www.openappmkt.com

Categories: Music Rec

Do you use Smart Playlists?

Music Machinery - Paul Lamere - Echonest - Fri, 07/30/2010 - 13:41

iTunes Smart Playlists allow for very flexible creation of dynamic playlists based on a whole boat-load of parameters. But I wonder how often people use this feature. Is it too complicated? Let’s find out. I’ve created a poll that will take you about 20 seconds to complete. Go to iTunes, count up how many smart playlists you have. You can tell which playlists are smart playlists because they have the little gear icon:

Don’t count the pre-fab smart playlists that come with iTunes (like 90′s music, Recently Added, My Top Rated, etc.). Once you’ve counted up your playlists, take the poll:

View This Poll
online surveys

Categories: Music Rec

I’m at Sushi Yasuda (204 E. 43rd St, at 3rd Ave, New York). http://4sq.com/5VMFI2

Dan Kantor - AOL Music - Fri, 07/30/2010 - 02:32

I’m at Sushi Yasuda (204 E. 43rd St, at 3rd Ave, New York). http://4sq.com/5VMFI2

Categories: Music Rec

Music Recommendation through Expert-based Collaborative Filtering

Xamat - Fri, 07/30/2010 - 00:07

In September I will be presenting the paper entitled "Towards Fully Distributed and Privacy-preserving Recommendations via Expert Collaborative Filtering and RESTful Linked Data" in the 2010 International Conference on Web Intelligence in Toronto. You can read the full paper here, but in this post I will try to give you a taste of what is hidden behind such a long title.

This paper should be understood as a continuation of my research on Expert Based Collaborative Filtering -- the so-called Wisdom of the Few. I recommend you take a look at my previous post on this issue before moving on.

So the basic idea from our previous work was to use domain experts as the only asset for creating neighborhood and predicting item utility in a similar way as is done in standard kNN collaborative filtering. We made some claims of how that method provided many practical advantages over standard approaches. We also claimed that the approach was scalable and flexible enough to be used in many domains. Unfortunately, at that point, we did not have time to implement and prove all that.

The current work presents a practical full-fledged implementation of the approach in the music domain. Our goal is to prove some of the previous claims as well as to stablish an architectural framework for expert collaborative filtering providing, among other things, 100% privacy protection.

The following screenshot will give you an idea of the application. In the client side, it is a Flex/Air stand-alone application that can work in most operating systems. You can rate music albums, see the ratings from the experts, and get personalized recommendations based on that. We also provide access to extended information for albums via links to lastfm as well as access to Linked Data resources from MusicBrainz and others.

The key architectural differences between standard and expert Collaborative Filtering are illustrated in the figure below. Note that in our expert CF, user ratings are kept in the client machine. On the other hand, expert ratings are downloaded into the local machine and the computation for the predictions is performed there avoiding any privacy breach.

The next figure gives some more details of how we implemented the solution in our case. Again, note that the server is only used to crawl and store expert ratings publically available on the web. Those ratings are then queried from the client through a REST-style web api. The computation of neighbors and predictions is then performed in the local machine.

You might be wondering where we got our expert ratings from. If in our previous work, we crawled our movie ratings from rottetomatoes, we now turned to metacritics. The figure below illustrates the number of ratings per critic. In the top positions, we can see AllMusicGuide with over 3500 ratings, or Pitchfork, Uncut, and Mojo, with over 3000.

I believe that expert collaborative filtering is a very flexible and valid paradigm in many domains. It can offer better results than other kinds of recommendations while solving many of the shortcomings such as scalability, privacy, or cold-start. We are currently working in other deployments in the mobile space, for example. But I will explain that in a future post.

Categories: Music Rec

I went from the first generation iPhone to the iPhone4. I saved...

Dan Kantor - AOL Music - Fri, 07/30/2010 - 00:06

I went from the first generation iPhone to the iPhone4. I saved something like 2 hours a day added up :)

Categories: Music Rec

The next music tastemakers – the computer programmers

Music Machinery - Paul Lamere - Echonest - Thu, 07/29/2010 - 16:32

There’s an interesting piece in the New Yorker about the future of listening. The article focuses on Pandora and MOG and the challenges of making the online listening experience. Author Sasha Frere-Jones concludes with this:

While using these services, I kept thinking about an early-eighties drum machine called the Roland TR-808, which has seduced generations of musicians with its heavy kick-drum sound and the oddly human swing of its clock. Whoever programmed this box had more impact on dance music than the hundreds of better-known musicians who used the device. Similarly, the anonymous programmers who write the algorithms that control the series of songs in these streaming services may end up having a huge effect on the way that people think of musical narrative—what follows what, and who sounds best with whom. Sometimes we will be the d.j.s, and sometimes the machines will be, and we may be surprised by which we prefer.

Read the article:

You, the D.J. Online music moves to the cloud.

Categories: Music Rec

Help researchers understand earworms

Music Machinery - Paul Lamere - Echonest - Thu, 07/29/2010 - 14:20

Researchers at Goldsmiths, University of London, in a collaboration with the BBC 6 and the British Academy, are conducting research to find out about the music in people’s heads, sometimes called ’musical imagery’. They want to know what songs are the most common, whether people like it or don’t, what triggers it, and if some people have music in their head all the time, etc.

To help researchers understand this phenomenon, take part in a questionnaire (and you could win £150 too). I took the survey, it took about 10 minutes. They do ask some rather personal questions that seem related to one’s tendency towards compulsive behavior. (yes, I do sometimes count the stairs that I’m walking up).

It looks to be an interesting research project. More details about it are here: The Earwomery.com

Categories: Music Rec

Best sliders in the city. w/ @gregory80 (@ Mark) http://4sq.com/4EKlwx

Dan Kantor - AOL Music - Thu, 07/29/2010 - 00:49

Best sliders in the city. w/ @gregory80 (@ Mark) http://4sq.com/4EKlwx

Categories: Music Rec

staff: Borked ID3 tags got you down? Now you can edit your...

Dan Kantor - AOL Music - Wed, 07/28/2010 - 22:57

staff:

Borked ID3 tags got you down? Now you can edit your Audio post’s track info and album art! Sweet.

Categories: Music Rec

Visual Music

Music Machinery - Paul Lamere - Echonest - Wed, 07/28/2010 - 10:47

The week long Visual Music Collaborative Workshop held at the Eyebeam just finished up. This was an invite-only event where participants did a deep dive into sound analysis techniques, openGL programming, and interfacing with mobile control devices.

Here’s one project built during the week that uses The Echo Nest analysis output:

(Via Aaron Meyers)

Categories: Music Rec

ANTICIPATING WHAT AVERAGE OPINION EXPECTS AVERAGE OPINION TO BE

comments on the social graph - Wed, 07/28/2010 - 07:34

At the IAB Rising Voices session last week I spoke on user-generated content and crowdsourcing and did a little experiment to demonstrate the wisdom of the crowds.

The beauty queens in the image above, were the winners of Miss Beach World. What I didn't share during the experiment is whether red, blue, or green won, came 2nd or came 3rd. I asked the Rising Voices (around 40 people last week) to guess the order the judges selected for position 1, 2, or 3.

This is a very different task to asking who they thought was prettiest, second prettiest, or third prettiest. The distinction is important. My aim was to see whether they could anticipate what average opinion expects the average opinion to be.The judges were defined as an 'average opinion' since they could not know who they were. They were asked to think who on average would win this type of contest?

In the table below you will see the options they could choose from.

Thankfully for me - the single largest block of guesses - around 40% of the crowd, chose the right answer (see comments for right answer). They correctly second guessed the way the judges chose.

•
This is an example of the application of collective intelligence, swarm logic, wisdom of the crowds - or whatever else you'd like to call it. More specifically, its what the celebrated economist J.M Keynes called the Beauty Contest. Instead of the usual sort of beauty contest, where women parade in front of a panel of judges, Keynes’ version is a post-modern contest involving the full participation of the public as real competitors.

Keynes' beauty contest happens through a fictional newspaper in which entrants are asked to choose a set of six faces from photographs of women that are the "most beautiful". Those who picked the most popular face are then eligible for a prize. Indeed, if all the other competitors are also aiming to win the prize, they are also looking at the problem from the same point of view.

Keynes likened the competitors in this beauty contest to professional speculators in financial markets. Keynes argued these speculators do not really attempt to predict what an investment will yield, but instead try to stay one or two steps ahead of average opinion:- they attempt to beat the market.

This type of intelligence - the hive mind - can be harnessed for crowdsouring, predictive markets, and creating social enterprises. Businesses will need to think of smart ways of truly capitalise on the latent intelligence that is buried deep underground in their firms. Mining this intelligence from your employees, stakeholders, and target market will be a key competitive advantage going forward. This is real social media.
Posted by Tony Effik

RT @extensionfm: New Release: SoundCloud Support! http://bit.ly/bXszh3

Dan Kantor - AOL Music - Tue, 07/27/2010 - 23:44

RT @extensionfm: New Release: SoundCloud Support! http://bit.ly/bXszh3

Categories: Music Rec

I don’t care what Foursquare says. @majman is definitely the mayor here (@ Gimme! Coffee)...

Dan Kantor - AOL Music - Tue, 07/27/2010 - 23:44

I don’t care what Foursquare says. @majman is definitely the mayor here (@ Gimme! Coffee) http://4sq.com/2VjgFT

Categories: Music Rec

New Release: SoundCloud Support

Dan Kantor - AOL Music - Tue, 07/27/2010 - 20:48

extensionfm:

We just released 1.5.2 to the Chrome extension gallery. This new release adds support for SoundCloud!

In their own words - “SoundCloud is a new online audio platform that lets music professionals receive, send & distribute their music”. In our words - SoundCloud has a ton of amazing music that you need to to listen to right now!

Support for SoundCloud works both on soundcloud.com as well as any site that has a SoundCloud widget embedded (like this one).

SoundCloud support is really exciting because it opens up a direct link from the artist’s studio into the listener’s music library. If we think back to when bands used to record music for ten’s of thousands of dollars in a studio, then produce millions of plastic discs, then ship those discs to thousands of stores, then have listeners spend 20 minutes trying to open the plastic surrounding those plastic discs, well anyway you get the point. Now artists can make music for the cost of a computer, upload it to SoundCloud and within seconds it’s inside their fans’ music libraries. Pretty incredible!

In addition to SoundCloud, this release also adds Tumblr oAuth support. Previously, logging into Tumblr meant giving us your username and password. With oAuth, you now just tell Tumblr you trust us and they give us a token to use on your behalf. You can untrust us (don’t know why you’d ever want to do that!) any time you want and the token will stop working. It’s a lot more secure this way. If you are already logged in to Tumblr inside the extension, you may want to consider logging out and then logging back in with oAuth.

We’d love to hear what you think about these new features. Leave us a comment here or on our UserVoice page.

Categories: Music Rec