Data Reveals How Men and Women Differ as Music Fans

February 10, 2014


"Men are from Mars and women are from Venus," as a book famously claimed.

Both of these genders agree, however, that the music of Bruno Mars is well worth a listen — it’s just about every other artist they seem to disagree on.

By analyzing the listening behavior of 200,000 anonymous music fans across a variety of services (self-reported as male or female), The Echo Nest director of developer platform Paul Lamere has drawn fascinating observations about the music, generally speaking, that men and women like to listen to.

His Music Machinery blog has the full story, as well as a full-sized version of the chart previewed above, but here are some key findings:

Only one artist falls in the top five for both genders: Bruno Mars. The same is true of most of the rest of music, according to this data — there’s just not a lot of overlap between the music men and women listen to the most.

About 30 percent of artists skew heavily towards male or female listeners. About 70 percent appeal at least somewhat to both genders.

These artists skew more “female” than any others in the top 1,000:

  • Danity Kane

  • Cody Simpson

  • Hannah Montana

  • Emily Osment

  • Playa LImbo

  • Vanessa Hudgens

  • Sandoval

  • Miranda Lambert

  • Sugarland

  • Aly & AJ

  • Christina Milian

  • Noel Schajris

  • Maria José

  • Jesse McCartney

  • Bridgit Mendler

  • Ashanti

  • Luis Fonsi

  • La Oreja de Van Gogh

  • Michelle Williams

  • Lindsay Lohan

These artists skew more “male” than any others in the top 1,000:

  • Iron Maiden

  • Rage Against the Machine

  • Van Halen

  • N.W.A

  • Jimi Hendrix

  • Limp Bizkit

  • Wu-Tang Clan

  • Xzibit

  • The Who

  • Moby

  • Alice in Chains

  • Soundgarden

  • Black Sabbath

  • Stone Temple Pilots

  • Mobb Deep

  • Queens of the Stone Age

  • Ice Cube

  • Kavinsky

  • Audioslave

  • Pantera

As Paul suggests, music apps and services can use this information to select more gender-neutral artists when they don’t know whether the listener is male or female.

If an app or service does know whether a person is male or female, they can serve up better music by tailoring playlists, streaming radio, recommendations, and more to artists prefered by that genre, and de-emphasizing those that aren’t.

Accounting for gender bias in both directions, the most popular five artists are: Bruno Mars, Rihanna, Justin Timberlake, Katy Perry, and Drake, in that order.

Paul has far more detailed analysis, so for the full story — including which genres skew strongly one way or the other — check out the full post on Music Machinery.

Paul Lamere Reports on Epic MIDEM Music Hack Day

February 7, 2014

We really love our Music Hack Days here at The Echo Nest, for a plethora of reasons, chief among them that it’s fun to watch talented visionaries focus their energies on building the future of music for a weekend and then demonstrate their creations to each other.

This most recent MIDEM Music Hack Day in Cannes, France produced a truly stunning array of music apps and hacks. Each of these events are special, as mentioned, but this one really stood out.

Our own director of developer platform and international music hacker Paul Lamere was on hand in the south of France with the rest of the l33t music hackers, which makes him the ideal person to take you on a tour through the best creations from MIDEM Music Hack Day, and the fruits of those who labored there to turn their ideas into realities for us to enjoy.

Paul Lamere’s Music Machinery: Let’s Go To France To Write Some Code

Photo by @neomoha

Fast Company: ‘The Next Big Thing In Music? Apps That Read Your Mind’

February 5, 2014

With tens of millions of songs to choose from, music fans need as much help as they can get to find songs that strike a chord — the perfect song for that person, at that time.

As you can read in this excellent report from Fast Company’s Co.Design, The Echo Nest director of developer platform Paul Lamere has been thinking a lot about the next solution to this problem: the “zero UI” music player — so named because, much like the FM radio, it won’t make you delve into a complicated interface to get music to play — but unlike the radio, it’ll play the right songs for you and your day.

"If you look where the music industry is going, music in the future will be played almost entirely on people’s phones," Paul told Co.Design. “And your phone knows a lot about you, which is data we can use to predict the music you like.”

Read more:

Follow The Echo Nest on Facebook or Twitter for more news and research.

Eventful Joins The Echo Nest’s Rosetta Stone

January 22, 2014

The world contains many databases about many things, to put it mildly. They’re great at talking to themselves, because, on a basic level, the rows and columns know what’s in the other rows and columns.

It’s a trickier proposition to make these databases talk to each other – and yet that’s precisely what has to happen, if music fans are going to be able to buy tickets to see the band whose song they just tagged or “liked” on a music service, to pick a couple examples of things people want to do.

Digital music is fragmented across a panoply of websites, apps, and social networks. But the same diversity that makes this such an amazing time for discovering music also hurts music fans, artists, and businesses, because each experience happens in a silo.

Rosetta Stone, from The Echo Nest, addresses the problem head-on, by helping all of this stuff work together. We’re announcing today that Eventful, a leading digital media company connecting consumers with entertainment, movies and local events, is now part of the Rosetta Stone platform. As a result, developers will be able to deliver the world’s most comprehensive list of local concert listings to music fans — and have that those listings better hook up with other services.

Eventful joining Rosetta Stone means its shows can appear in whatever other apps or services a music fan is using to listen, discover, or identify music. It also knows Twitter and Facebook, so it can put the official artist pages right into any music app, without the developer having to find them all.

With over 21 million registered users, Eventful became “the world’s largest collection of events,” with listings for everything “from concerts and sports to singles events and political rallies,” in part through an open API that extends its reach to over 7,000 partners.

As such, Eventful is a natural partner for The Echo Nest’s Rosetta Stone platform, which makes APIs even more open and connected by helping them to work much better with other companies’ APIs.

The result: a healthier music ecosystem that’s easier to build for — and that’s good for everyone.

If you’d like to integrate Eventful’s concert data into your app, service, or website right alongside the Rosetta Stone partners listed below, without having to figure out how to make all of those connections yourself, see our Rosetta Stone documentation for Eventful.

The Echo Nest Rosetta Stone Partner Sandboxes now include:

How P2P University, MIT, and NYU Analyzed Music Taste to Improve Learning

January 21, 2014

The folks at MIT Media Lab, NYU, and Peer 2 Peer University recently set out to teach the world how to manipulate music with a computer and a browser through interactive classes on PlayWithYourMusic.org.

When 5,282 people registered for the course, their suspicion that people would be interested in this were confirmed. Then, they had a new problem: how to split all of these people into groups, so that the people in each group would be into the same kinds of music. After all, one person’s beautiful bebop is another’s frantic nightmare, some people simply cannot abide reggae, and so on.

Before learning how to produce music together, these students first had to get along as music fans.

"We wanted to put them in groups based on their musical taste hoping to improve group cohesion and collaboration," writes P2P U. “We decided to use The Echo Nest since they have an API that helps with doing just that! The Echo Nest provides Taste Profiles – a collection of songs or artists representing a user’s musical preference. The Echo Nest can then relate one taste profile to another – higher scores mean that taste profiles are more alike.”

Their full report is worth a read for a few reasons:

  • It shows the need for (and a new application of) Taste Profile Similarity, which segments music fans, so that people with similar taste can be introduced to each other, among other reasons.

  • P2P U, MIT Media Lab, and the NYU Steinhardt faculty members behind PlayWithYourMusic.org found that using grouping people by Taste Profile had a positive side effect: “The idea of being grouped this way appealed to many learners who signed up, and they awaited being assigned to a group with much anticipation. This in turn resulted in higher engagements by the learners around musical interest.”

  • We appreciate a good case study as much as the next people; it’s always interesting to see what happens when the stuff we build gets used in the real world. The problem of splitting thousands of people into hundred groups based on musical taste is an interesting one, and widely applicable beyond the realm of music education.

PlayWithYourMusic is currently accepting students for its next session.

We’re Really Looking Forward to Music Hack Day Tokyo

January 17, 2014

Since we helped launch the popular Music Hack Day series as a founding organizer in 2009, we’ve been lucky enough to watch some of the smartest people in the world build every music app they could think of — most recently at our 5th annual Music Hack Day Boston.

One thing we’ve never seen is a Music Hack Day Tokyo, and neither has anyone else.

Japan is the world’s second biggest music market — one reason it’s a focus of The Echo Nest’s continued global expansion. Japan also happens to be the birthplace of the portable music revolution and home to many of the world’s leading technology companies and enthusiasts and a really vibrant music scene.

Its prominence in both music and technology makes Japan’s capital city a perfect Music Hack Day location. To help make this happen, we’ve partnered with the folks at Social Media Week Tokyo to pull this together. We’re extremely excited to see what gets made at Music Hack Day Tokyo using our API, and those of the other sponsor companies (so far, these include The Echo Nest, Gracenote, MusiXMatch, SendGrid, Social Media Week, and Spotify, with more to come). Music Hack Day will reach new developers, and with them, new ideas for music hacks and apps.

In particular, we’re looking forward to seeing what folks build using our new genres, which include at least 16 types of Japanese music.

Music Hack Days are regular events held in cities around the world, where programmers, hardware hackers, musicians, artists, and anyone else who’s interested in the future of music gathers to build new functional music technologies over the course of a single weekend. There were 15 of these last year, and they never fail to impress, in terms of what a room full of clever people can build with our platform.

We’ll see you there, or, rather, 私たちはそこにお会いしましょう

Registration is open for Music Hack Day Tokyo February 22nd and 23rd The Terminal 3F Wave Jingumae 3-22-12 Jingumae Shibuya-ku Tokyo, 150-0001

Image courtesy of The Terminal

The Future of Music Genres Is Here

January 16, 2014

We’ve always felt ambivalent about the word “genre” at The Echo Nest. On one hand, it’s the most universal shorthand for classifying music, because everyone has a basic understanding of the big, old music genres: Rock, Jazz, Classical, and so on.

On the other hand, those same basic genres — as helpful as they were for categorizing three rows of vinyl in a record store — are of little use to today’s music fans, as they stare into an abyss of 30 million songs from all over the world.

Asking for “Rock” is only slightly better than "Play me some songs that are music."

The Echo Nest API and playlist engine has long supported genre radio and the ability to browse music by “top terms,” which are the words most commonly used to describe a piece of music. They’re far more granular than the big, static genres of the past. We’ve been maintaining an internal list of dynamic genre categories for about 800 different kinds of music. We also know what role each artist or song plays in its genre (whether they are a key artist for that genre, one of the most commonly played, or an up-and-comer).

Today, we are opening up our genres through our API. Now, our customers and developer community can access a bunch of new genre-oriented features, including:

  • A list of nearly 800 genres from the real world of music
  • Names and editorial descriptions of every genre
  • Essential artists from any genre
  • Similar genres to any genre
  • Verified explainer links to third-party resources when available
  • Genre search by keyword
  • Ranked genres associated with artists
  • Three radio “presets” for each genre: Core (the songs most representative of the genre); In Rotation (the songs being played most frequently in any genre today); and Emerging (up-and-coming songs within the genre).

We’ll be offering these new genre features as enhancements to our Music Discovery & Personalization and Dynamic Music Data solutions, helping our partners deliver a better, more compelling music discovery experience to hundreds of millions of people.

Where did these genres come from?

First, it’s important to remember that The Echo Nest’s music intelligence platform continuously learns about music. Most other static genre solutions classify music into rigid, hierarchical relationships, but our system reads everything written about music on the web, and listens to millions of new songs all the time, to identify their acoustic attributes.

This enables our genres to react to changes in music as they happen. To create dynamic genres, The Echo Nest identifies salient terms used to describe music (e.g., “math rock,” “IDM”, etc.), just as they start to appear. We then model genres as dynamic music clusters — groupings of artists and songs that share common descriptors, and similar acoustic and cultural attributes. When a new genre forms, we know about it, and music fans who listen to our customers’ apps and services will be able to discover it right away, too.

Our approach to genres is trend-aware. That means it knows not only what artists and songs fall into a given genre, but also how those songs and artists are trending among actual music fans, within those genres.

About 260 of these nearly 800 genres are hyper-regional, meaning that they are tied to specific places. Our genre system sees these forms of music as they actually exist; it can help the curious music fan hear the differences, for instance, between Luk Thung, Benga, and Zim music.

These new genres are rolling out today. You can listen to them right now on Every Noise At Once, where we’ve been previewing them, or on Music Popcorn, which is also pretty fun:

To keep your ears stimulated, check out the "Genre A Day" web app, or subscribe to our brand new “Genre A Day” Twitter.

As fun as they are, Every Noise At Once, Music Popcorn, and Genre A Day are demonstrations. We can’t wait to put these new genres into the hands of the hundreds of millions of music fans who use the apps and services powered by our world-leading music intelligence, which now includes the best, most accurate genres available anywhere.

To find out how to implement these new genres in your service or app, head over here for more information.

What Music Looks Like Without an Interface

January 14, 2014

If you have yet to encounter the “zero UI” or “no UI” phenomenon, it’s basically about designing software outside of the traditional model of “a screen plus some controls.”

In such an environment, instead of running an app, opening a search box, and typing in something to listen to, one simply might just listen to the music that’s already playing, because it’s already likely to be something you’ll enjoy at that particular moment.

Rdio’s You FM, powered by The Echo Nest, is a big first step in this direction. It creates a single station based on your Taste Profile — thus “You FM.”

Going forward, the possibilities for “zero UI” music are set to expand, now that our phones now know where we are, what we are doing, where we are going, and more — all of which can be used to play the right music to the right person at the right time.

The Echo Nest director of developer platform Paul Lamere has been thinking about what a “zero UI” music player looks like for many months now.

Check out his post on Music Machinery for more on where he sees “zero UI” going, and how to keep tabs on his progress as he builds a zero-UI music app. You can also read it on Medium.

Stay tuned for more interesting things from The Echo Nest.

2013: The Echo Nest’s Biggest Year Yet

January 9, 2014

In 2013, The Echo Nest’s music intelligence leadership hit the next level. We doubled down on our world-leading Music Discovery & Personalization and Dynamic Music Data solutions. We introduced Music Audience Understanding, which extends our leading personalization technology to help music services improve marketing and advertising. And, we expanded around the world.

Let’s take a stroll past the year’s greatest hits…

  • We were thrilled to add over 20 new customers through the course of the year, including Gaana, Microsoft, Nuance, and Rhapsody.

  • We now serve over one billion API queries per month. Queries to our platform have increased tenfold over the past year.

  • We we took “Musical Identity” from concept to solution. Our Taste Profile technology builds a deep understanding of each (anonymous) listener on a music service to improve their overall experience, and adds value to the services themselves. Taste Profile adoption increased tenfold.

  • We launched a new client services team to support our 70-plus customers and partners, while also kicking off a formal customer training and developer/partner program.

  • As anyone who reads this blog probably already knows, we did a ton of work in the world of Genres in 2013. Through our API, you can now explore over 800 dynamic, ever-changing micro-genres of music (check them out here), along with several hundred dynamic, region-specific genres supporting our continued global expansion into over 50 countries including Denmark, Germany, India, Japan, Poland, Sweden, and Venezuela.

  • We helped Sirius XM, the biggest music subscription service in the world, allow listeners to customize expert-curated stations with MySXM.

  • We unveiled new music attributes such Acousticness, Currency, Discovery, Artist Location, and regionalized Hotttness.

  • We announced a partnership with Getty, offering direct access to Getty’s amazing images through our API.

  • We were all over the news. Some of the most interesting coverage included Every Noise At Once, our investigation into how music has changed since the ’50s, our early work into Audience Understanding with movies, and a hilarious social media dust-up between our director of developer community Paul Lamere and fans of the girl group Fifth Harmony.

Our amazing, brilliant, insane, music-obsessed team was responsible for all of this. Much love to each and every one of you.

To stay updated on our progress in 2014, follow us on Twitter and like us on Facebook.

Hottest Songs & Biggest Music Discoveries of 2013

January 6, 2014

Did you notice the calendar switch from 2013 to 2014? This seems to happen every year, bringing a deluge of end-of-year lists, especially where music is concerned. Still, we promise you have yet to see anything like the 2013 “year in music” maps below.

The Echo Nest collects more detailed, sophisticated data about all of the recorded music in the world than anything else, affording us a unique vantage point for analyzing what transpired in music last year. The following end-of-year lists, available in both map and playlist form, were created not by asking a music expert what music she personally liked to hear last year, but by listening to all the music released this year and reading everything people everywhere said about it, which is part of how The Echo Nest operates.

Rather than having one person or a roundtable of magazine editors weigh in on the year’s most impactful music, our system accounts for how the whole internet feels about it.

1,000 Hottest Songs of 2013

The following map, created by The Echo Nest data alchemist Glenn McDonald as part of Every Noise At Once, showcases the hottest 1,000 songs of 2013, grouped by artist, with larger, darker text indicating artists with hotter songs and/or multiple songs on the list. You can listen to each artist directly on the map (with 30-second samples for all and full tracks for Rdio subscribers):

For a lean-back version of this experience, the following playlist plays the “hotttest” artists of 2013 (our proprietary attribute includes three t’s in the word “hotttness”):

 

You might have noticed that you haven’t heard of some of these, which is due in part to the worldwide nature of what The Echo Nest sees (although we can also dial in certain regions).

"This is pulling from everything we know — worldwide, all genres," explains McDonald. "American listening is a huge factor because we’re a huge part of the listening world, but we’re not limited to that here… I totally expected to see a lot of Latin artists, and we do. Part of the reason it’s interesting is that you don’t see a lot of other multiregion lists pulling from all over."

In other words, the above map reflects the hottest songs on planet earth last year, not just in one particular country.

500 Biggest Musical Discoveries of 2013

Another way we look at music is by identifying songs that took the world by surprise, in that they grew quite popular despite having been recorded by artists who weren’t yet well-known.

The following list shows the artists whose stars started rising fast enough in 2013 to make The Echo Nest’s “Discovery” list, and grabs the 500 who had the “hotttest” tracks of the year.

In other words, these are the relatively unknown artists that The Echo Nest predicted would make a splash in 2013, which actually did make a splash.

"We had Lorde [on the Discovery list] before ‘Royals’ hit,” recalls McDonald. “We had that song ‘Clarity’ [by Zedd] before it was a hit. We had Luke Bryan before he was big, and Icona Pop. We had Chvrches before their album came out. I think that Neighborhood song ‘Sweater Weather’ we had before it was big. That Martin Garrix song “Animals” is huge in Europe and we had that.”

To hear the 500 biggest musical discoveries of 2013, you can check out this new page on Every Noise at Once:

And here’s our 2013 discovery playlist on Rdio:

 

Astute observers will notice at least one oddity in the above map. What on earth is Darius Rucker doing on there? Is the man once known as “Hootie” no longer officially famous?

"Yeah, his prominence as a solo artist indicates that it’s less than Hootie’s," said McDonald. "And discovery is always proportional — it’s hotttness disproportionate to familiarity. In his case, he’s still relatively familiar, but his song took off super quickly relative to his fame as Darius Rucker."

The Echo Nest’s “discovery” attribute correctly predicted that Lorde, Icona Pop, Chvrches, and others would break through in 2013. One-step-ahead hipsters and label types who wish to tap its power in 2014 are in luck: Our discovery list updates each week throughout the year on Rdio, allowing them to hear the next Lorde before she hits the big time.

"If you listen to every week, you would have known about a fair number of artists that everybody else discovered later," said McDonald, "and I would expect that to continue."