• T156@lemmy.world
      link
      fedilink
      English
      arrow-up
      0
      ·
      4 months ago

      Only slightly though. It hardly seems practical to try and infer gender from names, in a way where it can’t be obtained through historical records, or the user.

      • skisnow@lemmy.ca
        link
        fedilink
        English
        arrow-up
        0
        ·
        4 months ago

        For a given individual, sure. If you’re trying to do some statistics over a whole group that you have no other record for, it could be useful.

        • bss03@infosec.pub
          link
          fedilink
          English
          arrow-up
          0
          ·
          4 months ago

          Sounds like those statistics output would the heavily biased by whatever process you were using to turn names into genders. In short, a bad idea.

          • TangledHyphae@lemmy.world
            link
            fedilink
            arrow-up
            0
            arrow-down
            1
            ·
            4 months ago

            “Since the dataset isn’t 100% perfectly annotated for analysis, we should give up the whole project entirely.”