Twitters algorithm is a little more complex it seems than just 'is this single tweet offensive'. Entire accounts appear to be flagged and every reply they make gets marked.
That's true, but the end result, no matter how complicated their algorithm is, is that they don't seem to be doing a very good job of distinguishing offensive from inoffensive tweets.
Very true. Sure they catch some bad stuff, but more often than not it slips past.
They're also doing a very very bad job at responding to reports. If someone makes a threat and you report it, they instantly email, literally the same second you click the button, that they found nothing wrong.