You are viewing a single comment's thread from:
RE: Steem Sincerity - Improved Anti-Spam API
AWESOME! I applaud this so much!
but I am still sad my cuddle-bot (delivering tons of upvotes and barely ever leaving a comment without upvoting) has made it into the top 500 biggest spammers
I don't think there's many who interact with the kitten who actually see her as spam... but I understand how an algorithm may get to that impression.
P.S.: maybe some of this data could be incorporated into the rating to determine how spammy an account actually is?!
at the moment a very obnoxious spammer (@tomole444 for example) does not make it into the top 500 (despite ~5k comments and ~650 flags received) while my cuddle-delivery service does get caught with "only" 160 comments and zero flags!
I'd also like to have seen this account with a lower spam score, and higher bot score. I will add it to the bot training set. ;)
These factors you mention are included in the rating, but the accuracy and effectiveness is limited by the training set, which I'm in the process of expanding.
I see! Thanks for the feedback... expanding the training data by reasonable but not too biased examples will be the major challenge (as it seems to be with AI).
I'm curious to see how the detection will improve over time. Thanks a ton for the efforts you are making on this!