Comment by greggman | Hacker News Reader

Comment by greggman | Hacker News Reader

Do any of the music services not suck at suggestions and or auto playlists?

I tried Spotify, Google Music, Amazon, Pandora and all of them drove me batty.

The most common problem is just bad selection. For example I picked "Daily Lift" on Spotify expecting uplifting songs. First song was about woman finding out man is cheating on her. Second song is about woman thinking of x while sleeping with new guy. Neither was remotely uplifting.

Another example, on Google Music I play Prince. Pick "related" and get rap. I have nothing against rap but it's not even remotely related to Prince except in maybe some possibbly racist way.

Pandora had the problem on playing the same songs and if you ban the songs you just end up getting different mixes of the same song.

Yet other issues is "more like this" never works. If I'm playing say a ballad and I pick "more like this" I expect more ballads but instead all the music services just give you songs by artists someone judged as popular with people who like the artist you're currently listing too so you might get dance or rock or rap or anything and not actually "more like this"

I've cancelled all of them as I didn't find them useful because of those issues.

To your first issue, there are three ways I can think of that music recommendations are usually built: - collaborative filtering: i.e. People who listened to x tend to listen to y, so if you like x we will recommend y - metadata: x and y share multiple genre tags, or have contributed to releases in common, or release music in the same time period, etc - audio data: x and y have similar tempo, prominent instrument timbres, absence or presence of vocals, time signature, major or minor-ness, key

However, I've never heard of lyrics being used as data or metadata for determining similarity of tracks.

For one thing, it's not necessarily a common use case. I did college radio and we would do themed shows where all the songs are about food, for example, but 99% of the time of I listen to a song that happens to mention ice cream, I don't want/need the next song to mention ice cream.

On top of that, it's not obvious what type of lyrical similarity is desired. Do you want to match lyrical sentiment? (Happy songs with happy songs, whether they're about girls or cars or cooking) Or theme (relationship songs, positive or negative) or words in common or phrases in common.

It's definitely an interesting idea that I'd love to see toyed with, but I'm not surprised that its not, given how much effort it might be for an unclear and possibly uncommonly desires result. Not to mention that Spotify usually doesn't have a canonical source for lyrics of a given track anyway.

Reply on news.ycombinator.com