Hi, this is a pretty cool initiative. Any steps or ideas to classify posts directly as spam instead of accounts?
By the way are you reachable on any discord server? I'm working with Machine Learning on Steemit Blockchain data, too. Mainly trying to find good content, rather than punishing bad actors :-D. I'm interested in exchanging ideas if you like.
Btw, I found a bot that tries to achieve a similar goal to your initiative (maybe you can get in touch, too):
https://steemit.com/introduceyourself/@duplibot/introducing-duplibot-reducing-rewards-on-comment-spam
(By the way I did find this by using my own content search bot @hounddog ;-) cough.
I decided that since, unlike email, the senders of messages can't be spoofed in Steem comments, and that account intentions would change slowly if at all, that accounts were a better level of granularity than comments for classification. I do see a lot of merit in an additional layer for scoring individual comments though, and these could in fact feed into an account classifier.
I'm in the steemdevs server in discord, but am not very familiar with it, and also steem.chat as @andybets. I'd be interested in what you're working on. :)