Gender Specific Listening

One of the challenges faced by a music streaming service is to figure out what music to play for the brand-new listener.  The first listening experience of a new listener can be critical to gaining that listener as a long time subscriber. However, figuring out what to play for that new listener is very difficult because often there’s absolutely no data available about what kind of music that listener likes. Some music services will interview the new listener to get an idea of their music tastes.

beats-enrollment

Selecting your favorite genres is part of the nifty user interview for Beat’s music

However, we’ve seen that for many listeners, especially the casual and indifferent listeners, this type of enrollment may be too complicated. Some listeners don’t know or care about the differences between Blues, R&B and Americana and thus won’t be able to tell you which they prefer. A listener whose only experience in starting a listening session is to turn on the radio may not be ready for a multi-screen interview about their music taste.

So what can a music service play for a listener when they have absolutely no data about that listener? A good place to start is to play music by the most popular artists.  Given no other data,  playing what’s popular is better than nothing. But perhaps we can do better than that. The key is in looking at the little bit of data that a new listener will give you.

For most music services, there’s a short user enrollment process that gets some basic info from the listener including their email address and some basic demographic information. Here’s the enrollment box for Spotify:

Music_for_everyone__-_Spotify_-__Private_Browsing_

Included in this information is the date of birth and the gender of the listener. Perhaps we can use basic demographic data to generate a slightly more refined set of artists. For starters, lets consider gender.  Let’s try to answer the question: If we know that a listener is male or female does that increase our understanding of what kind of music they might like?  Let’s take a look.

Exploring Gender Differences in Listening
Do men listen to different music than women do? Anecdotally, we can think of lots of examples that point to yes – it seems like more of One Direction’s fans are female, while more heavy metal fans are male, but lets take a look at some data to see if this is really the case.

The Data – For this study,  I looked at the recent listening of about 200 thousand randomly selected listeners that have self-identified as either male or female.  From this set of listeners, I tallied up the number of male and female listeners for each artist and then simply ranked the artists in order or listeners. Here’s a quick look at the top 5 artists by gender.

Top 5 artists by gender

Rank All Male Female
1 Rihanna Eminem Rihanna
2 Bruno Mars Daft Punk Bruno Mars
3 Eminem Jay-Z Beyoncé
4 Katy Perry Bruno Mars Katy Perry
5 Justin Timberlake Drake P!nk

Among the top 5 we see that the Male and Female listeners only share one artist in common:Bruno Mars.  This trend continues as we look at the top 40 artists. Comparing lists by eye can be a bit difficult, so I created a slopegraph visualization to make it easier to compare. Click on this image to see the whole slopegraph:

click for full chart

click for full chart

Looking at the top 40 charts artists we see that more than a quarter of the artists are gender specific. Artists that top the female listener chart but are missing on the male listener chart include: Justin Bieber, Demi Lovato, Shakira, Britney Spears, One Direction, Christina Aguilera, Ke$ha, Ciara, Jennifer Lopez, Avril Lavigne and Nicki Minaj. Conversely, artists that top the male listener chart but are missing on the top 40 female listener chart include: Bob Marley, Kendrick Lamar, Wiz Khalifa, Avicii, T.I. Queen, J.Cole, Linkin Park, Kid Cudi and 50 Cent. While some artists seem to more easily cross gender lines like Rihanna, Justin Timberlake, Lana Del Rey and Robin Thicke.

No matter what size chart we look at – whether it is the top 40, top 200 or the top 1000 artists – about 30% of artists on a gender-specific chart don’t appear on the corresponding chart for the opposite gender.  Similarly, about 15% of the artists that appear on a general chart of top artists will be of low relevance to a typical listener based on these gender-listening differences.

What does this all mean?  If you don’t know anything about a listener except for their gender, you can reduce the listener WTFs by 15% for a typical listener by restricting plays to artists from the gender specific charts.  But perhaps even more importantly, we can use this data to improve the listening experience for a listener even if we don’t know a listener’s gender at all.  Looking at the data we see that there are a number of gender-polarizing artists on any chart. These are artists that are extremely popular for one gender, but not popular at all for the other.  Chances are that if you play one of these polarizing artists for a listener that you know absolutely nothing about, 50% of the time you will get it wrong.  Play One Direction and 50% of the time the listener won’t like it, just because 50% of the time the listener is male.  This means that we can improve the listening experience for a listener, even if we don’t know their gender by eliminating the gender skewing artists and replacing them with more gender neutral artists.

Let’s see how this would affect our charts.  Here are the new Top 40 artists when we account for gender differences.

Rank Old Rank Artist
1 2 Bruno Mars
2 1 Rihanna
3 5 Justin Timberlake
4 4 Katy Perry
5 6 Drake
6 15 Chris Brown
7 3 Eminem
8 8 P!nk
9 11 David Guetta
10 14 Usher
11 17 Maroon 5
12 7 Jay-Z
13 13 Adele
14 9 Beyoncé
15 12 Lil Wayne
16 23 Lana Del Rey
17 25 Robin Thicke
18 24 Pitbull
19 27 The Black Eyed Peas
20 19 Lady Gaga
21 20 Michael Jackson
22 10 Daft Punk
23 18 Miley Cyrus
24 22 Macklemore & Ryan Lewis
25 28 Coldplay
26 16 Taylor Swift
27 26 Calvin Harris
28 21 Alicia Keys
29 29 Imagine Dragons
30 30 Britney Spears
31 44 Ellie Goulding
32 31 Kanye West
33 42 J. Cole
34 41 T.I.
35 52 LMFAO
36 32 Shakira
37 35 Bob Marley
38 54 will.i.am
39 36 Ke$ha
40 39 Wiz Khalifa

Artists promoted to the chart due to replace gender-skewed artists are in bold. Artists that were dropped from the top 40 are:

  • Avicii – skews male
  • Justin Bieber – skews female
  • Christina Aguilera – skews female
  • One Direction – skews female
  • Demi Lovato – skews female

Who are the most gender skewed artists?

The Top 40  is a fairly narrow slice of music. It is much more interesting to look at how listening can skew across a much broader range of music.  Here I look at the top 1,000 artists listened to by males and the top 1,000 artists listened to by females and find the artists that have the largest change in rank as they move from the male chart to the female chart. Artists that lose the most rank are artists that skew male the most, while artists that gain the most rank skew female.

Top male-skewed artists:
artists that skew towards male fans

  • 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

Top female-skewed artists:
artists that skew towards female fans

  • 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

Gender-skewed Genres

By looking at the genres of the most gender skewed artists we can also get a sense of which genres are most gender skewed as well.  Looking at the genres of the top 1000 artists listened to by male listeners and the top 1000 artists with female listeners we identify the most skewed genres:

Genres most skewed to female listeners:

  • Pop
  • Dance Pop
  • Contemporary  Hit Radio
  • Urban Contemporary
  • R&B
  • Hot Adult Contemporary
  • Latin Pop
  • Teen Pop
  • Neo soul
  • Latin
  • Pop rock
  • Contemporary country

Genres most skewed to male listeners:

  • Rock
  • Hip Hop
  • House
  • Album Rock
  • Rap
  • Pop Rap
  • Indie Rock
  • Funk Rock
  • Gangster Rap
  • Electro house
  • Classic rock
  • Nu metal

Summary

This study confirms what we expected – that there are differences in gender listening. For mainstream listening about 30% of the artists in a typical male’s listening rotation won’t be found in a typical female listening rotation and vice versa. If we happen to know a listener’s gender and nothing else, we can improve their listening experience somewhat by replacing artists that skew to the opposite gender with more neutral artists.  We can even improve the listening experience for a listener that we know absolutely nothing about – not even their gender – by replacing gender-polarized artists with artists that are more accepted by both genders.

Of course when we talk about gender differences in listening, we are talking about probabilities and statistics averaged over a large number of people. Yes, the typical One Direction fan is female, but that doesn’t mean that all One Direction fans are female.  We can use gender to help us improve the listening experience for a brand new user, even if we don’t know the gender of that new user. But I suspect the benefits of using gender for music scheduling is limited to helping with the cold start problem. After a new user has listened to a dozen or so songs, we’ll have a much richer picture of the type of music they listen to – and we may discover that the new male listener really does like to listen to One Direction and Justin Bieber and that new female listener is a big classic rock fan that especially likes Jimi Hendrix.

update – 2/13 – commenter AW suggested that the word ‘bias’ was too loaded a term. I agree and have changed the post replacing ‘bias’ with ‘difference’

  1. #1 by Nikke Osterback on February 11, 2014 - 10:43 am

    Is this based on US or global data?

    • #2 by Paul on February 11, 2014 - 3:53 pm

      it is not global, but not entirely confined to the US market. I may make another pass to restrict things to a single country in the future.

  2. #3 by Michael Carratt on February 12, 2014 - 8:58 am

    Interesting, and I appreciate your caveats in the last paragraph, but I’m not sure I feel 100% comfortable with this sort of profiling. For instance, I bet ethnicity might be a good way of getting further refinement like this, but that’s clearly the wrong side of the line for most people to be happy about it.

    • #4 by Paul on February 12, 2014 - 9:07 am

      Indeed – making predictions about an individual based on aggregate data is always risky and potentially inflammatory. There are lots of examples of racist recommendations that result from blind reliance on data to drive recommendations. There are two challenges – one is to understand what we can learn from the data – but the other, and this maybe the bigger challenge, is to figure out the best way to use this knowledge without crossing the creepy or inappropriate line.

      • #5 by gbellny on February 19, 2014 - 3:52 pm

        Drill the refinement to its lowest denominator possible. You will need Facebook like gender tracking, ethnicity tracking, and social economic status tracking. You will then eliminate most recommendations issues. As always, you want this data to have the potential to drive incremental ROI.

  3. #6 by Alex Cannon (@acannon828) on February 12, 2014 - 7:26 pm

    Will you do a similar study for age? Or even both age and gender? Do your users vary enough in age to make a study like this worthwhile? I would guess age-based profiling could also be a useful solution to the cold start problem. I’m interested to see what those charts would like, especially which artists span generations and more specifically which of today’s contemporary artists are popular with the older folk. Maybe old ladies are secretly listening to Daft Punk at their bridge club gatherings…

  4. #9 by AW on February 13, 2014 - 12:33 am

    I am questioning your choice of the word bias, which typically implies some unfairness. Wouldn’t calling it gender differences be less loaded?

    • #10 by Paul on February 13, 2014 - 7:27 am

      AW – that’s a good point.

    • #11 by Paul on February 13, 2014 - 8:30 am

      AW – after pondering this a bit, I went and updated the post to remove the loaded term ‘bias’. thanks for the feedback!

  5. #12 by Alex Ruthmann (@alexruthmann) on February 13, 2014 - 8:10 pm

    New technical research term: “listener WTFs”. :)

  6. #13 by Alex on February 14, 2014 - 12:02 pm

    I remember last.fm doing a similar graph a few years ago where they plotted where your listening tastes compare to people of your age and gender. I found it fascinating (and still do) how female artists are delegated to “female listeners” and male artists skew toward the “male listeners” part of the chart, though less dramatically than the female artists. I wonder what causes this sort of predilection.

    • #14 by Paul on February 14, 2014 - 12:05 pm

      Indeed, I’ve noticed some patterns related to the gender of the artists. This post on group playlisting has some observations along that line.

  7. #15 by Rick TheRev Barlow on February 18, 2014 - 7:07 am

    I’d love a list like this for the UK but as the artists are predominantly global it’s still very useful data.
    I’m a mobile DJ doing mostly weddings, parties etc (I’m 52 and my Ayia Napa days are way behind me!) and I can see myself reffering to this list at the beginning of an evening until I gauge my audience.
    Thanks very much.

  8. #16 by Sophie Campbell on February 26, 2014 - 2:42 pm

    So I must be male then…

  9. #17 by Person on February 27, 2014 - 1:52 am

    It’s sex, not gender.

    • #18 by Paul on March 3, 2014 - 12:43 pm

      I understand there’s a debate about this, but OED backs up the usage of gender. In the Oxford English Dictionary, gender is defined as, “[i]n mod. (esp. feminist) use, a euphemism for the sex of a human being, often intended to emphasize the social and cultural, as opposed to the biological, distinctions between the sexes.”,

  10. #19 by hippyaids on March 3, 2014 - 10:23 am

    Reblogged this on hippyAIDS and commented:
    Interesting stuff..

  11. #20 by Youngdoe on March 3, 2014 - 7:05 pm

    I have no idea how big the actual effect could be on your statistics, but I do think that a fairly substantial number of female listeners are disguised as male in user data such as these. Firstly, I personally know a number of couples where the Spotify subscription is registered to the male in the relationship, and secondly, as a teacher, I’ve noticed that a whole bunch of kids (boys and girls alike) use their parents’ Spotify, which without exception has turned out to mean their father’s when I’ve asked them. Now, I’ll admit that this is some fairly on anecdotal evidence, but if you look at the Spotify demographics you’ll notice a huge discrepancy between male and female users. In the 12-19 age group the total number of users is low, but equally distributed between the genders, but as the users get into their twenties there are almost twice as many registered male users than female. This also goes for users in their thirties. Now, I’m not saying that boys don’t like, say, P!nk, a whole lot of us probably do, but I do believe that a rather large number of “male” P!nk listeners on Spotify could actually be that male user’s girlfriend or daughter. Just a thought.

    • #21 by Paul on March 3, 2014 - 7:24 pm

      Youndoe – this is a good point. I discussed exactly this issue in the age-specific listening post. What I said about confounding issues for age, applies for gender as well:

      • There’s a built-in popularity bias in music services. If you go to any popular music service you will see that they all feature a number of playlists filled with popular music. Playlists like The Billboard Top 100, The Viral 50, The Top Tracks, Popular New Releases etc. populate the home page or starting screen for most music services. This popularity bias inflates the apparent interest in popular music so, for instance, it may look like a 64-year-old is more interested in popular music than they really are because they are curious about what’s on all of those featured playlists.
      • The age data isn’t perfect – for instance, there are certainly a number of people that we think are 64-years-old but are not. This will skew the results to artists that are more generally popular. We don’t really know how big this affect is, but it is certainly non-zero.
      • People share listening accounts – this is perhaps the biggest confounding factor – that 64-year-old listener may be listening to music with their kids, their grand-kids, their neighbors and friends which means that not all of those plays should count as plays by a 64-year-old. Again, we don’t know how big this effect is, but it is certainly non-zero.
  12. #22 by Rush fan on March 12, 2014 - 11:12 am

    Having been to several Rush concerts, surprised not to see Rush in the skewing-male list. How close did they come to the cut-off?

    • #23 by Paul on March 12, 2014 - 11:45 am

      Rush is the 69th most male skewed artist.

      • #24 by Rush fan on March 12, 2014 - 12:14 pm

        Thanks for the quick reply!

        So Rush skews heavily male, but not three-standard-deviations male. Interesting that they’re Delaware’s favorite band (and that George Thorogood and the Delaware Destroyers aren’t.)

Follow

Get every new post delivered to your Inbox.

Join 1,006 other followers

%d bloggers like this: