Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Spotify’s Discover Weekly: How machine learning finds new music

hackernoon.com

Post reply on HN
Print view View original

201–210 of 275 posts

Re: Spotify’s Discover Weekly: How machine learning finds new music

#201

Post by ambivalents »

kamilszybalski wrote: post #196
sumitgt wrote: post #184

Earlier quoted context omitted.

I prefer how Google Play Music does suggestions and wish Spotify could adopt some elements of the same. Eg. GPM does suggests things like: 1) Looks like you are at work, here's some music without lyrics for concentration. 2) Looks like you are at home, here's some relaxing music. .. and so on. Also Spotify sometimes gets things too right, and it stops me from discovering new music. GPM does a better job introducing n…

I have three main criticisms of Spotify, just in case there's a Spotify PM reading. 1. I hear repeat songs in my discover all the time, this isn't ideal. I curate my own playlists for moods and know that i'm getting when I play those playlists, surfacing songs I've manually curated in my discover doesn't add value to my experience. 2. I wish I could more easily surface the discover playlists of my friends or those wh…

Just want to reiterate gripe #3. The Daily Mixes were, at first, the Best Thing Ever. But that was like a year ago, and they don't seem to have changed at all since then. I've listened to a lot of different music this past year, but keep hearing the same old songs on all the Daily Mixes. I'd expect them to update in more overt ways as my tastes evolved.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#202

Post by blkhp19 »

nobleach wrote: post #172

I find that my music tastes can vary too much for Spotify. While working, I mostly listen to Electronic music. But I can also take a hard right turn and listen to Hall and Oates... or Fleetwood Mac, or Steely Dan. Then some form of 80's throwback. But as far as recommendations go, I really only want to expand in that first genre of Electronic Music. I don't want Jethro Tull to be recommended to me. My feed used to be…

I have this exact same problem. Please Spotify, fix this.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#203

Post by hammock »

nobleach wrote: post #172

I find that my music tastes can vary too much for Spotify. While working, I mostly listen to Electronic music. But I can also take a hard right turn and listen to Hall and Oates... or Fleetwood Mac, or Steely Dan. Then some form of 80's throwback. But as far as recommendations go, I really only want to expand in that first genre of Electronic Music. I don't want Jethro Tull to be recommended to me. My feed used to be…

Don't you have Daily Mixes? These are smart playlists created by Spotify organized roughly into genres, and you have can up to six - depending on how diverse your listening habits are. Right now I have:

1 Electronic, 2 Pop, 3 R&B, 4 Indie, 5 Rap, 6 Country/Americana

Note they aren't named like this, I did that. Spotify identifies them only by a number and a few of the artists contained within. You can find them in the app on your Home screen or under Your Library > Your Daily Mix.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#204

Post by steve-benjamins »

landtuna wrote: post #132
steve-benjamins wrote: post #89

As an artist, Discover Weekly has been the best thing to ever happen to me. Every Monday I get a big infusion of listeners (around 5,000)— many of who stick around and check out my other music :) Prior to that, the best press I could get was the tedious process of cold-emailing bloggers (a practice which is now dying off).

Haha - read your comment, looked at your username, opened Spotify, and "Purification Ritual" is the first song in my Discover Weekly.

Hah— no way! That's amazing... made my morning :)

Re: Spotify’s Discover Weekly: How machine learning finds new music

#205

Post by steve-benjamins »

jcb1973 wrote: post #167
jcb1973 wrote: post #166

Earlier quoted context omitted.

And now thanks to discussion of Discover Weekly, I've discovered Steve Benjamins... Thanks!

And "Hi Steve!" - listening to "Purification Ritual" now...

Hi! :)

Re: Spotify’s Discover Weekly: How machine learning finds new music

#206

Post by hammock »

sumitgt wrote: post #184
nobleach wrote: post #172

I find that my music tastes can vary too much for Spotify. While working, I mostly listen to Electronic music. But I can also take a hard right turn and listen to Hall and Oates... or Fleetwood Mac, or Steely Dan. Then some form of 80's throwback. But as far as recommendations go, I really only want to expand in that first genre of Electronic Music. I don't want Jethro Tull to be recommended to me. My feed used to be…

I prefer how Google Play Music does suggestions and wish Spotify could adopt some elements of the same. Eg. GPM does suggests things like: 1) Looks like you are at work, here's some music without lyrics for concentration. 2) Looks like you are at home, here's some relaxing music. .. and so on. Also Spotify sometimes gets things too right, and it stops me from discovering new music. GPM does a better job introducing n…

>GPM does suggests things like: 1) Looks like you are at work, here's some music without lyrics for concentration. 2) Looks like you are at home, here's some relaxing music.

Spotify does this too. Under Browse, many of the suggested playlists are context-dependent and will change depending on the time of day.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#207

Post by spike021 »

I've been using Apple Music the past 8 or so months because somehow while I was finishing up school I ended up on their student discount plan and not Spotify's.

I really miss Spotify's Discover Weekly. Apple Music (AM) has a similar feature, called "New Music Mix", but it's never as accurate.

While I was still using Spotify heavily last year, almost every week I'd duplicate the Discover Weekly playlist so I could keep that exact mix because a majority of the songs would really fit my current music tastes. Nowadays with AM I only duplicate a New Music Mix playlist once every month, if that. It's ridiculous how uninspired the playlist from Apple is and oftentimes it includes music that isn't similar to anything I listen to.

Discover Weekly is the one feature that would bring me back to Spotify and let me ditch AM once my discount period expires.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#208

Post by hammock »

kamilszybalski wrote: post #196
sumitgt wrote: post #184

Earlier quoted context omitted.

I prefer how Google Play Music does suggestions and wish Spotify could adopt some elements of the same. Eg. GPM does suggests things like: 1) Looks like you are at work, here's some music without lyrics for concentration. 2) Looks like you are at home, here's some relaxing music. .. and so on. Also Spotify sometimes gets things too right, and it stops me from discovering new music. GPM does a better job introducing n…

I have three main criticisms of Spotify, just in case there's a Spotify PM reading. 1. I hear repeat songs in my discover all the time, this isn't ideal. I curate my own playlists for moods and know that i'm getting when I play those playlists, surfacing songs I've manually curated in my discover doesn't add value to my experience. 2. I wish I could more easily surface the discover playlists of my friends or those wh…

>1. I hear repeat songs in my discover all the time

Something is wrong. Discover Weekly is supposed to have only songs you have never listened to, even once. That's how it works for me.

Re: Spotify’s Discover Weekly: How machine learning finds new music

#209

Post by dvlsg »

nobleach wrote: post #172

I find that my music tastes can vary too much for Spotify. While working, I mostly listen to Electronic music. But I can also take a hard right turn and listen to Hall and Oates... or Fleetwood Mac, or Steely Dan. Then some form of 80's throwback. But as far as recommendations go, I really only want to expand in that first genre of Electronic Music. I don't want Jethro Tull to be recommended to me. My feed used to be…

You could try this tool from hate5six: http://hate5six.com/sage - historically, they've only worked with hardcore / metal music, but this appears to be a new tool which expanded out to 200k artists across all types. I managed to find 3 folk artists which I am loving, and had never heard of from either Google or spotify. Curious if it is broad enough to work for your taste in music.

(not affiliated with them in any way)

Re: Spotify’s Discover Weekly: How machine learning finds new music

#210

Post by ar-nelson »

hammock wrote: post #203
nobleach wrote: post #172

I find that my music tastes can vary too much for Spotify. While working, I mostly listen to Electronic music. But I can also take a hard right turn and listen to Hall and Oates... or Fleetwood Mac, or Steely Dan. Then some form of 80's throwback. But as far as recommendations go, I really only want to expand in that first genre of Electronic Music. I don't want Jethro Tull to be recommended to me. My feed used to be…

Don't you have Daily Mixes? These are smart playlists created by Spotify organized roughly into genres, and you have can up to six - depending on how diverse your listening habits are. Right now I have: 1 Electronic, 2 Pop, 3 R&B, 4 Indie, 5 Rap, 6 Country/Americana Note they aren't named like this, I did that. Spotify identifies them only by a number and a few of the artists contained within. You can find them in th…

These solve the problem somewhat, but, in my experience, they only play songs I've already listened to. So listening to songs outside the genres I want recommendations for will still ruin Discover Weekly's usefulness as a discovery system.

I used to love Discover Weekly, and found a lot of great music through it, but it's gotten less useful over time. A few things that would improve it:

• Multiple Discover playlists sorted roughly into genres, like the Daily Mix but only containing never-before-heard music

• Treat Discover Weekly like a radio station, with thumbs-up and thumbs-down buttons

• Once I've listened to a track a few times, stop suggesting it. At this point I can usually predict what my Discover Weekly playlist will be: all of the songs that have showed up on it before, but that I didn't like enough to click "+" on.

Post reply on HN