PeerTube Picks is now available on the official Firefox Add-ons page! Firefox users no longer have to worry about losing their data when the browser closes:

FireFox add-on link

The name PeerTube Picks was chosen through collaboration with the PeerTube Lemmy community. This add-on provides video recommendations using a cosine similarity algorithm based on videos you’ve watched and liked. It aims to predict which videos you’re likely to engage with—either by watching for longer periods or hitting the like button.

Updates: The PeerTube Picks icon now appears next to the search bar on any PeerTube page. Clicking it opens a list of recommended videos, ranked by engagement and relevance.

A new Options page allows you to:

-Download or upload your video watch history

-Delete your watch history (recommended occasionally to refresh your recommendations)

I’m open to suggestions and contributions—feel free to share ideas or improvements!

  • AbnormalHumanBeingA
    link
    fedilink
    arrow-up
    2
    ·
    20 days ago

    Love this! I had been thinking about how it could be possible to do a self-directed algorithm via add-on like that, but it never was more than a quick silly idea in my head. I’m really happy to see this appearing as an official add-on!

    • Cattail@lemmy.worldOP
      link
      fedilink
      arrow-up
      2
      ·
      20 days ago

      I tried to pick the simplist algorithm just to get working concept and because I believed something basic could work well, but I definitely left room for more algorithm.

      There’s multiple parts but I tried to get the data collection down, tracking watch time, likes/dislikes, and even if the it’s a video or Livestream. There is a glitch with tracking how long a live stream has been watched, but Livestreams aren’t relevant yet so I haven’t bothered to fix it.

      This add on is meant to be open source so it can grow and evolve so it can be implemented into other fediverse projects and so people can improve on it and make it their own. I can put other algorithms in, just seeing how the reception goes.

      I do believe we should collect our own data and run our own algorithms