←back to thread

Information operations directed at Hong Kong

(blog.twitter.com)
1116 points whatok | 1 comments | 19 Aug 19 18:11 UTC | HN request time: 0s | source
Show context
29_29 ◴[19 Aug 19 18:47 UTC] No.20740549[source]▶
I was recently in Beijing and noticed when posting on Instagram many bot accounts posting "Shame on Hong Kong" in Chinese.

This is a Facebook problem too. If you work at facebook please help!

replies(2): >>20740564 #>>20740575 #
bertil ◴[19 Aug 19 18:50 UTC] No.20740575[source]▶
Flag all the accounts that seem suspicious. The more signal, the easier for Threat Intelligence to identify them.
replies(1): >>20740616 #
29_29 ◴[19 Aug 19 18:53 UTC] No.20740616[source]▶
I did, but I feel like this could be solved with machine learning.
replies(3): >>20740631 #>>20740696 #>>20742135 #
1. lucb1e ◴[19 Aug 19 21:48 UTC] No.20742135[source]▶
Flagging bot accounts does not strike me as something a computer would be able to do. If they notice that the machine learned to recognize keywords, they'll use different ones; if they notice it recognizes IP addresses, they'll use different ones; etc. It seems very similar to spam classification to me.