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

191–200 of 275 posts

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

#191

Post by ethbro »

delegate wrote: post #182

The thing with any 'recommendation' system like Discover Weekly is that while it recommends based on past preferences, the recommendations have the effect of influencing and reinforcing the musical tastes and at some point one will notice that one's taste in music has been entirely manufactured by the algorithm, week by week. This is not just in music, the filtering 'according to preferences' is ubiquitous in today's…

Did you read the article?

Only 1 (audio analysis) of the 3 models (collaborative, nlp sentiment, audio) doesn't mix in recommendations from non-you sources, thereby surfacing new music to your attention.

It explains why I tend to like Discover too. Precisely because it doesn't duplicate my exact tastes.

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

#192

Post by fredoliveira »

charlesdm wrote: post #189
whatok wrote: post #185

Earlier quoted context omitted.

Google Music has location-based recommendations. Not sure why Spotify couldn't incorporate something similar.

Does location matter when dealing with music taste? Just because I'm in Nashville doesn't necessarily mean I love country music?

Music you listen to at the park may be different from the music you listen to while programming at work, for example. So yes.

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

#193

Post by probably_wrong »

eru wrote: post #134
probably_wrong wrote: post #104

Earlier quoted context omitted.

> You can use this site to find out what genres your favorite artists are categorized as That's my problem right there: my favorite song right now is a musician's piano cover of one of his own songs. His music is usually electronic, which I don't like, but I love this one song. So Spotify will recommend me electronic music from other artists, which of course does not fit my song. Repeat for every author. I liked one…

Pandora works song-by-song (and is not bound by genres).

It's also not available outside the US :-/

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

#194

Post by reitanqild »

I read a few threads down but couldn't find it so here it goes:

I'm quite unimpressed by this feature. It knows full well that I almost only listen to music without lyrics (trance genre to be specific) when I work.

Sometimes I try the automatic playlists including discover weekly and what do they play? 50% vocal.

I skip as soon as I recognise it but they never learn. I also mostly play from a precompiled list containing only instrumental trance but even that is not enough.

At least they are in good company. Google has seen all my searches, my photos and my mail since before I met my wife and yet for years they figured out the most relevant ads they could show me was for dating sites :-/

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

#195

Post by markussss »

micahjonas wrote: post #174
markussss wrote: post #140

The biggest problem with the Discover Weekly is its inability to understand _why_ you're listening to a specific subset of music. It might not be that your taste in music suddenly changed, or that you discovered a new genre that you're incredibly interested in, even though your most listened to genres or songs changed for a few weeks, or your listening patterns changed for a few weeks. A few examples: I'm Norwegian,…

Maybe don't listen to the discovery weekly playlist for the week and just listen to other playlists you like. If you listen to the genre because it's in your weekly playlist, than spotify is probably going to think you like those songs. Search for some open playlist you like and don't listen to the discovery weekly. In my experience spotify is fairly good a taking the hint. One alternative would be the daily selectio…

Thanks, but this is what I've been doing for the last few months, although I have also listened to music that is somewhat similar in genre (Norwegian music, electronic, hip-hop, pop, etc). I don't think I should stop listening to the music I like in order to manipulate the algorithms into giving me the music I like and want to listen to. It's counter-intuitive.

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

#196

Post by kamilszybalski »

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…

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 whom I follow. I know that my friends like similar music but the small differences might provide insightful curation data and help me discover new music, so, it'd be interesting to see the data on discovery curation through social connections.

3. There's some chatter about daily mixes here. I find that my daily mixes don't change enough. I'll try them once, two times, then I'll churn from using that feature.

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

#197

Post by MSM »

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'm very similar- look into the Daily Mixes that are created, this solves that issue for me.

Right now I have six different mixes and each one of them seem to be a grouped into a different genre (or sub genre).

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

#198

Post by jaideepsingh »

One thing I want in Spotify recommendation engine is proper multilingual support. I have a varied/eclectic taste in English/Hindi/Punjabi music that spans decades and there are many sub-sub-genres that Discover Weekly doesn't capture. It keeps recommending me Telugu/Tamil song, probably based on beats, but I cannot understand them haha

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

#199

Post by kspy »

I find that with spotify I get a more consistent variety of music. However I actually pay and use google music primarily. Wish there was a feature on google music (besides feeling lucky or radio) that had curated content like spotify does. I'm usually able to find at least a song I like that comes up in the discover weekly

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

#200

Post by scrooched_moose »

pj_mukh wrote: post #175
markussss wrote: post #140

The biggest problem with the Discover Weekly is its inability to understand _why_ you're listening to a specific subset of music. It might not be that your taste in music suddenly changed, or that you discovered a new genre that you're incredibly interested in, even though your most listened to genres or songs changed for a few weeks, or your listening patterns changed for a few weeks. A few examples: I'm Norwegian,…

I really wish I could get Spotify to "forget" or "reset" my preferences. When I first started using Spotify, I listened to a lot of slow calming music (because I was working). Now ALL my Discover weekly's are just 'Iron and Wine', 'The National' derivatives. Its made Discover Weekly useless to me.

I have the same issue with Iron and Wine and I don't get why. Every recommendation engine I've tried decides I absolutely love them, no matter what seed I start with or what songs I like/dislike.

I don't mind Iron and Wine but they are definitely a 'meh' for me, so it gets frustrating when they dominate every playlist. And, disliking/thumbs down never seems to get rid of them.

Are they generic enough that the algorithm finds something similar between them and everything I like?

Post reply on HN