Live data from Hacker News

The lie of music discovery algorithms

zeynepevecen.dev

71–80 of 198 posts

Re: The lie of music discovery algorithms

#71

Pandora, Pandora, Pandora. No other service for me worked to reveal new songs and artists I did not know about that nailed my taste. But Pandora relies on manual tagging by music experts. Fantastic, but probably not very scalable.

Indeed. The Music Genome Project never got beyond ~250k songs IIRC.

Re: The lie of music discovery algorithms

#72
post #17

In the age of internet, engagement optimization and recommendation algorithms create a new way that we are affected by the behaviour of others. That annoying dark pattern on a piece of software you use? Because there are people who fall to it, clicking on an ad or "engaging" more. That stupid show that keeps being recommended to you? Because a lot of people just sit on the couch, watching something on the list that d…

Yess! Thank you for commenting. I am very interested in this topic. Please do share with me if you find any interesting ways to explore new music for your taste

This probably won't work for most people, but as I mostly like metal, I simply check all metal releases that seem slightly to my tastes according to the subgenre. Then when this sampling seems at least somewhat positive, I play the full album after release. That usually ends in sampling songs from 30 albums, listening to ten albums, and buying 1-2 every Friday. Never had an algorithmic recommendation system that worked for me.

Re: The lie of music discovery algorithms

#73
post #39

Music discovery has never worked for me, for the simple reason it's the lyrics, not the music. I listen to anyone speaking truth, (the truth I believe, of course), and that gives me a wide disjoint range of music, but they are all singing about political social truths. Marvin Gaye, Public Enemy, Rage Against The Machine, Beyonce, The Stranglers, The Jam, Psychic TV... It's the lyrics, and now today, we finally have t…

You might like folk punk - check out Pat the Bunny. I feel like there are two kinds of singers - people who are good at singing, and people who have something to sing about. You and I, I think, prefer the latter.

A perfect example of lyric dominant music, which I own a hug amount, and feeds right into hip hop and then Johnny Cash and The Clash.

Re: The lie of music discovery algorithms

#74
post #54

I’ve used everything, new and old media: Spotify, Napster, CMJ, pitchfork, bandcamp, allmusic, mojo, SoundCloud, beatport, last.fm, Apple Music… Nothing beats that one friend who used to DJ and still obsessively digs crates.

i’ll echo this. that dj friend or like i said in a different comment, your local record store employees. college radio stations. and just other people. it really is that simple.

Especially, college radio and other free-form community radio stations.

People who feel they have a calling to be a DJ sometimes actually do.

I have a reasonable list of TuneIn stations (mostly US) that provide my favorite “discovery”.

Re: The lie of music discovery algorithms

#75

Pandora, Pandora, Pandora. No other service for me worked to reveal new songs and artists I did not know about that nailed my taste. But Pandora relies on manual tagging by music experts. Fantastic, but probably not very scalable.

Grooveshark. Pandora was miss-or-ding-the-side-of for me. Grooveshark always seemed to grab me songs that I NEVER would have discovered on my own, but that resonated with me somehow. It was also a lot easier to find particular versions of songs, or indie music (particularly before Soundcloud became popular). The benefits of not having to kowtow to music industry IP BS (until it was destroyed by it).

Re: The lie of music discovery algorithms

#76

Music discovery has never worked for me, for the simple reason it's the lyrics, not the music. I listen to anyone speaking truth, (the truth I believe, of course), and that gives me a wide disjoint range of music, but they are all singing about political social truths. Marvin Gaye, Public Enemy, Rage Against The Machine, Beyonce, The Stranglers, The Jam, Psychic TV... It's the lyrics, and now today, we finally have t…

That's a very good point, I also love discovering with lyrics. What I tried to do is to find some connections between the image and music, maybe some connection we as humans cannot see right away.

I've been wondering how well a word2vec on song lyrics would work; just completely ignore the music and pair up subject matters.

Re: The lie of music discovery algorithms

#77

Pandora, Pandora, Pandora. No other service for me worked to reveal new songs and artists I did not know about that nailed my taste. But Pandora relies on manual tagging by music experts. Fantastic, but probably not very scalable.

last.fm found me some of my favorite bands of the last 15 years.

Re: The lie of music discovery algorithms

#78
post #57
post #17

In the age of internet, engagement optimization and recommendation algorithms create a new way that we are affected by the behaviour of others. That annoying dark pattern on a piece of software you use? Because there are people who fall to it, clicking on an ad or "engaging" more. That stupid show that keeps being recommended to you? Because a lot of people just sit on the couch, watching something on the list that d…

I'm not sure how the Spotify recommendation algorithm works at all, but for some reason I imagined them doing fancier things than looking at my liked songs and finding similar ones. I would've thought they'd build a profile of you, and then find similar user profiles and show you songs those folks liked that you hadn't found yet. That's gotta be how they do it, right? I'm probably wrong.

I have no specific insider knowledge, but a decade+ ago they bought a company called the Echo Nest that was developing some of the best audio signal analysis algorithms around, I assume much of that influenced their recommender system.

Nowadays, they have a quite busy research department so I would imagine that recommendation is quite fancy indeed: https://research.atspotify.com

Re: The lie of music discovery algorithms

#79

Pandora, Pandora, Pandora. No other service for me worked to reveal new songs and artists I did not know about that nailed my taste. But Pandora relies on manual tagging by music experts. Fantastic, but probably not very scalable.

I was about to say that I've been pretty ok with Pandora so far. My wife thinks I "use it weird" as I mainly listen to the Shuffle station and have mostly various artists in my collection. Whereas she has styles and categories. And that's mostly because I don't want to listen to "Mid-90's Grunge", I want Soundgarden, Pearl Jam, etc.

However, even in the various artist stations, they do play artists "similar to" as well. Which is how I started listening to stuff like Murder By Death, Eilen Jewell, Bakar, Black Pumas, and others.

Re: The lie of music discovery algorithms

#80

No music discovery algorithm has satisfied me. All data-driven approaches make predictions based on historical data. Personally I enjoy being exposed to entirely new genres and sounds I've never heard before, instead of variations on genres I've listened to a lot. My solution: listening to NTS, an eclectic online radio station, where diverse artists create playlists.

I agree. Here’s a discovery tool I made to traverse NTS tracklists linked by common tracks ;)

https://www.barneyhill.com/pages/nts-tracklists/

Post reply on HN