• bamboo@lemm.ee
    link
    fedilink
    English
    arrow-up
    0
    ·
    4 months ago

    The algorithms are what makes these services. Most interactions aren’t searching and selecting something specific or intentional, they’re just opening a fire hose and expecting the algorithm to pick content they find entertaining for them. It requires the algorithm to have a lot of information, both about the specific user, and about similar users.

    • threelonmusketeers@sh.itjust.works
      link
      fedilink
      English
      arrow-up
      0
      ·
      4 months ago

      Would there be some way to have the algorithms localized to the user (or instance)? If data needs to be compared between users, would there be some way to anonymize the data first?

      • bamboo@lemm.ee
        link
        fedilink
        English
        arrow-up
        0
        ·
        4 months ago

        It’s a bit tricky but I think a privacy preserving algorithm is possible. Simply put, the more data available, the better an algorithm can be.