Every day I still have to block spam bots on Twitter :/ They always follow the same patterns, and can be spotted at a glance. I thought spam filtering was already a solved problem 10 years ago (and we have better ML nowadays)...
Show this thread
Some fake activity detection problems are difficult, e.g. detecting click fraud for displays ads. Even then, the ad industry is doing really well on these issues (often using logistic regression). But Twitter bot detection is not difficult, esp. because accounts are permanent
-
-
why do you think it is?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
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.