Tracks that you might like

works for you now: https://listenbrainz.org/recommended/tracks/Alsweider/top_artist :slight_smile:

1 Like

Hello,

Thx for this amazing work. I was waking for this kind of open technologies for so long time and I looking forward to see them integrated in other project as funkwhale o/

  • I have a question about “Tracks of artists that are popular in ListenBrainz will show up more in the playlist”. Is this a choice or a technical issue ?

This is a amazing idea. But using I think using user based tags is very limited. When I look a the incredibles results of the spotify algorithm I see a source of very precise recommendation : http://everynoise.com/

Don’t know how to help but would love to o/

I have a question about “Tracks of artists that are popular in ListenBrainz will show up more in the playlist”. Is this a choice or a technical issue ?

IIRC, it is inherent in the collaborative filtering algorithm – the basic idea of collaborative filtering is that “some users liked these tracks, so you might like them as well”. Popularity of tracks is an inherent part of this premise. But, I don’t see that as a bad thing – I don’t think because of this limitation we’re only going to get popular tracks recommended, but instead popular tracks within your taste range. If that makes sense…

This is a amazing idea. But using I think using user based tags is very limited. When I look a the incredibles results of the spotify algorithm I see a source of very precise recommendation :

You are quite right! We had hoped that when we built tags/genres that some tools (Picard, etc) allows submitting tags to us, but that hasn’t really happened. This is really a typical chicken and the egg problem – which came first?

If there is no compelling use case for tags/genres then people will not submit them. But if we build a compelling use case (e.g. this genre recommender) and people start using it, it gives them a reason to submit tags so that more of the music they love gets picked up by the algorithm. And if the algorithm does a better job, more people will come and use our recommendations… and the cycle continues.

It is this kind of cycle that I hope we can stimulate with the recommendations. There are plenty of ways in which the MusicBrainz data can be improved and if we can provide cool tools that expose data hole and then couple them with tools to submit the data that is missing, we’ll improve the database overall as we go.

We’ll see how it this plays out.

Don’t know how to help but would love to o/

Do you happen to know how to program in python?

3 Likes

I’m beginning, so I don’t know a lot :s

1 Like

It would be cool to get recommendations based on whole listen history, not just last week or month listens. Or with small timebased weight discount.

Also did you think about use AcousticBrainz data?

Yes they did : this use acoustibrainz data : https://github.com/metabrainz/troi-recommendation-playground in the ab-similarity patch
It as the advantage to allow the discovery of very unknowns artists o/

3 Likes

As far as the link of the recommendation engine with AcousticBrainz mentioned at

is there any description about how it works?

2 Likes

On similar subject

3 Likes

installation instruction are in the repo.

 sudo python3 -m troi.cli --help
Usage: cli.py [OPTIONS] COMMAND [ARGS]...

Options:
  --help  Show this message and exit.

Commands:
  info      Get info for a given patch
  list      List all available patches
  playlist  Generate a playlist using a patch PRINT: This option causes...
  test      Run unit tests

You can also explore the recommendation algorithms though Similar recordings to - "Return to Nowhere" by Charlotte De Witte - AcousticBrainz

1 Like

Thanks for the feedback: do you know how to provide data in case they are missing? Via Picard or are there any other ways?

AcousticBrainz offers GUI and command line submission tools, see Downloads - AcousticBrainz

The upcoming Picard 2.7 will also have the ability to submit the audio analysis to AcousticBrainz.

3 Likes