I made a Lemmy instance with a custom algorithm that keeps only the top 20% most unique (=interesting?) posts. It does this by calculating a similarity score between every post on my instance and all posts that came before it. The top 80% of posts with the highest self-similarity get removed instantly.

The idea would be that this allows me to cut through the noise that’s running through the communities, similar to how xkcd-signal attempted to do 20 years ago.

The instance is mostly meant for reading, not posting. So it has a very open federation policy (for now).

If anything, this is experimental. So please let me know what you think! You can see the type of stuff that gets removed in the modlog (https://lemmy.coffee/modlog).

  • anon6789@lemmy.worldEnglish
    2·
    2 days ago

    I do look to have made it to your feed now! It deleted my 3 posts that were photos with short blurbs and kept my news article that is mostly text.

    We rarely get the meme type posts, but if your setup is looking at anything like text:photo ratio, that could be doing it.

    I have most meme communities block myself, so I understand how overtaking they can be to a feed. 😁

    I’m interested in what you’re doing because I am interested in news and politics, but it would be nice to get rid of most of the garbage US news and the dupe posts, and let a better variety of news come in. I’ve gone to keyword blocking, but while I have “Trump” blocked, I’d still like to see things from other countries about their responses to his actions., for example.

    • coffeeadminOPAEnglish
      2·
      2 days ago

      I do very few things explicitly, I just punish self-similarity in a very specific way. I guess posts with actual text in the body are just more unique, given all previous posts on the instance.

      Maybe using the filtered posts as a base in combination with some client side keyword blocking will be useful? The keyword blocking would be much more individual for each user.