Yep, that “paper” isn’t even wrong. One tragedy of all this is that, at the moment, only the companies can fully study phenomenon such as the behavior of recommendation algorithms. There are some great external studies that do give us a sense—but that’s all we get. Yet.https://twitter.com/random_walker/status/1211262124724510721 …
-
-
LOL to anyone pretending to study recommendation algorithms without being logged in. It’s plausible YouTube’s has gotten better – partly because we highlighted the problem when they had their head in the sand. I also don’t think it’s fixable without “sacrificing” some engagement.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I wish, but in reality no. Only the company can access how the algorithm works, which results were retrieved and ranked, which version was used etc. I used to work in a large tech company and determining who saw what when and why was basically impossible for us too
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
In principle a panel study is “easy”, IFF you can use fake accounts (TOS violation I presume), and might have validity issues (unknowable unless you’re Google or already have done it with a real panel!). I’d kinda like to see it tried, though.
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.