Content
@
0 reply
0 recast
0 reaction
Varun Srinivasan
@v
Spam filtering is coming to Warpcast. Over the last 3 months, we've labelled thousands of spammy accounts by hand and @akshaan has carefully trained an ML model to do this automatically. We're rolling out this model starting today, and it will significantly improve the user experience.
91 replies
267 recasts
1551 reactions
Colin
@colin
How will false positives be handled? Is there manual review in the loop at all (eg for appeals?) Can a spam-labelled account ever be labeled good in the future?
3 replies
0 recast
52 reactions
Linda Xie
@linda
+1, would also like to know this
1 reply
0 recast
12 reactions
Varun Srinivasan
@v
the goal is to be like gmail, where the filtering works for 99.999% and you have the ability to turn off filtering to double check that nothing important was missed. we'll also periodically rescore accounts, so if there was a mis classification you can earn your way back out.
2 replies
0 recast
2 reactions
Satoshi Tomatomoto
@tomato.eth
Will people have a way of knowing whether they've been labelled as a spam account? One of the most frustrating things about Twitter has been the uncertainty about when and why people are being shadowbanned. I hope we don't repeat that here.
1 reply
0 recast
0 reaction
Jahkay
@jahkay
I could be reading this wrong, so my acc gets marked as spam due to false positive I have to earn my way back out even though it’s a computing error?
0 reply
0 recast
0 reaction
