[maxwell-neumann]

I’ve experienced something similar in attempting to report very explicit and outrageously racist posts and comments. Zero action on blatant neo-Nazism (including specific threats of violence), and several lost appeals. However, far more benign posts and comments that don’t really violate the ToS are often flagged. This is quite prevalent on Instagram especially, which is quite worrying as it’s acting as a radicalisation tunnel for large numbers of impressionable young people. It’s almost as if the algorithm attempts to throw you into a far-right rabbithole because they know it boosts engagement.

[zamber]

That's exactly what happens. The algo does not judge how hurtful a rabbithole may be - it optimizes for engagement with some moderation sprinkled on top. I've tried to make my facebook feed palatable for a couple months and eventually passed up on trying. I'd rather IM my family about cat photos than engage with their fringe political views. Same goes for colleagues on LinkedIn.

Tentacrul did a good video on it and more across the years https://m.youtube.com/watch?v=MPyJBJTHyO0&pp=ygUWZmFjZWJvb2s...