One of the few subscription services I would happily pay more for, for the recommendations alone.
Last.fm turns 20
81–90 of 178 posts
Re: Last.fm turns 20
#82Earlier quoted context omitted.
That's the way music-map.com works, and it is absolutely fantastic. But no, that is NOT the way these other services recommend things. Spotify, for example, recommends music that it thinks is related, but not necessarily liked by both groups of people. For example, a person who likes Black Sabbath, and really technical instrumental metal, probably doesn't like the comparatively simpler slipknot. While some people who…
So I put in Silver Jews, and expected to get probably the #1 result "Purple Mountains" which is also David Berman, and then pavement and some Malkmus as recommends. So I don't know how well that works. Coheed and Cambria seemed fairly good. I was expecting Thursday as a top result and got it. I put in "Mom Jeans" and a totally very different sounding band but on the same label who tour together and got "Just Friends"…
Yeah, Last.fm is really good for playing a playlist from a single scene. It's not necessarily a single genre, just bands who tour together, or guest on each other's tracks.
They used to go pretty deep too, like bringing in bands from 20 years before that influenced the current one.
It's not necessarily the greatest for bands that are selling out stadiums as there's too much interference from Clear Channel, but it's great for small to midsize scenes which tend to have shows from 100-1000, since those tend to be more defined.
Re: Last.fm turns 20
#83Still use last.fm. Most "You might like this" algorithms go straight for the low-hanging fruit, and often fail to take any kind of nuance into account. I can't tell you how many of the streaming services will see my Black Sabbath play history and immediately recommend, "If you like Black Sabbath, you should love...Slipknot!" But I've never had a real person make that mistake, because a real person who looks at my las…
This sounds like a fairly easy optimisation, actually. Whereas a human goes "Oh, so you mentioned A, B, and C, but not the otherwise popular D" and conditions on all that information, a simple recommendation system would just go "ah I see you didn't mention popular D, that must be because you don't know about them!"
Should be fairly easy to adjust the recommendation system so that it conditions on what you specifically did not mention, assuming that the most popular of that stuff you know about already.
Re: Last.fm turns 20
#84Still use last.fm. Most "You might like this" algorithms go straight for the low-hanging fruit, and often fail to take any kind of nuance into account. I can't tell you how many of the streaming services will see my Black Sabbath play history and immediately recommend, "If you like Black Sabbath, you should love...Slipknot!" But I've never had a real person make that mistake, because a real person who looks at my las…
Last.fm has a lot of these "Human recommendation" mechanisms. they are just kind of indirect. For exple, those humans could be
- People with whom you share recent top artists -> the "neighbours" feature
- People who also like that obscure favourite track of yours -> the "X listen to Y a lot" feature (or even just a delightful Shout on that track)
I often just convert the Loved ones from their "Top 100 Tracks" into a Spotify playlist (I may even filter it by genre beforehand)
The whole point is you don't have very similar taste to them. Still, you can find some totally unexpected gems.
Re: Last.fm turns 20
#85Contrary to popular belief Last.fm never really died (and I hope it never will), however it lost years ago its most valuable thing: *its own streaming service*.
It was just perfect at everything, was it finding new releases, discovery obscure gems, or play your favorite things all over. It was so magical that you could hardly believe it was computer generated.
Also, it was a wonderful "sane" social network where music and only music was at its heart: no vanity metrics (eg: counting likes) / vanity egos (eg: influencers) or purely material interests (eg: make money from this or that).
Anyway, it's sad it lost the streaming war pretty soon. Maybe it was just too genuine to compete with services driven by dark patterns, suspicious agendas, and mostly, greed.
Wait, is this a metaphor of the old internet versus the present state of digital affairs? Or am I just getting nostalgic here?
I don't know. Long live Last.fm!
111,920 Scrobbles from 9,137 Artists since Jul 2006.
Re: Last.fm turns 20
#86Earlier quoted context omitted.
I did the same recently after seeing it was possible. 150,000 scrobbles for me, which I thought was a lot until I saw your count! https://www.last.fm/user/carldr
Aw shucks,low compatibility. https://www.last.fm/user/unspotted
Only 72k for me, but there was a time for several years where I wasn't listening to any music on my computer. Something that working from home has seriously changed :D
Re: Last.fm turns 20
#87Still use last.fm. Most "You might like this" algorithms go straight for the low-hanging fruit, and often fail to take any kind of nuance into account. I can't tell you how many of the streaming services will see my Black Sabbath play history and immediately recommend, "If you like Black Sabbath, you should love...Slipknot!" But I've never had a real person make that mistake, because a real person who looks at my las…
Pandora was the best for recommendations. They stopped it being available in the UK over a decade ago, made me sad!
Re: Last.fm turns 20
#88Still use last.fm. Most "You might like this" algorithms go straight for the low-hanging fruit, and often fail to take any kind of nuance into account. I can't tell you how many of the streaming services will see my Black Sabbath play history and immediately recommend, "If you like Black Sabbath, you should love...Slipknot!" But I've never had a real person make that mistake, because a real person who looks at my las…
I've found most recommendation systems in general don't grasp the distinctions in genre that are in metal, or the stylistic differences. Most stuff is just tagged "METAL", when there is a huge difference between grind, funeral doom, or atmo-black. Even within a genre there can be differences it doesn't really capture, like tech-death: you might call Beyond Creation and Warp Chamber both tech-death, but in reality the…
It depends on how the recommendation system defines its music genres.
Spotify uses audio spectral features to automatically delineate tracks into styles.
Last.fm and RateYourMusic (who added recommendations recently) rely on human taggers. So, they may give you better results genre-wise.
Re: Last.fm turns 20
#89Earlier quoted context omitted.
I did the same recently after seeing it was possible. 150,000 scrobbles for me, which I thought was a lot until I saw your count! https://www.last.fm/user/carldr
Aw shucks,low compatibility. https://www.last.fm/user/unspotted
I've got high compatibility with carldr.
Re: Last.fm turns 20
#90Still use last.fm. Most "You might like this" algorithms go straight for the low-hanging fruit, and often fail to take any kind of nuance into account. I can't tell you how many of the streaming services will see my Black Sabbath play history and immediately recommend, "If you like Black Sabbath, you should love...Slipknot!" But I've never had a real person make that mistake, because a real person who looks at my las…
Two things I like to see trailed in music recommendation algorithms would be:
1. Associations happen at a song level. At the moment when artists are recommended you get what I call the "Red Hot Chilli Peppers" effect. That is, the artist that basically everyone seems to have in common in their playlists is RHCP. Instead, I think the recommendations should be more granular, at a song level. Artists can diverge quite wildly in style between individual songs (Ween being an extreme example of this). Take for example Planet Caravan by Black Sabbath (https://www.youtube.com/watch?v=SvrOzYtnLMA) this is great song but wildly different from say "War Pigs". In fact, it's a dubby, groovy slow jam.
2. Weight follow on plays more highly. So taking War Pigs in the point above. I listen to Planet Caravan and it makes me think of this great remix of Wicked Game by Trentemoller (https://www.youtube.com/watch?v=ph4z3u7IwrM). A totally unrelated artist and genre yet somehow linked in my mind. My assumption is that people that listen to Planet Caravan would also have a high likelihood of enjoying the Wicked Game remix because it has a similar... vibe I guess?
Anybody want to collaborate on building a recommendation engine around these two points? I'd be more than happy to record what I listen to as training data for it.