in meatspace humans historically lean heavily on clear, hard-or-costly-to-fake visual cues for ingroup / kinship-group sorting but Twitter's algorithms seem able to sort us into strongly felt kinship groups with little of that kind of data how can we learn to see like Twitter
nah, not hashtags and search, more "who to follow", RT surfacing (which is algorithmically influenced now) and like surfacing (which was always 100% algorithmic). prolly "the algorithm" gets credit for some of people's own sorting activity but it does seem to have developed
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.