Dan Romero
@dwr.eth
A few other thoughts 1. We use a machine learning algorithm to classify spammy users. 2. That requires a manual input when new spam "metas" emerge. 3. Best way to model spam (and fraud or any other "gaming" of a system) is like an organism that evolves based on the environment (the social network) and the various inputs into the environment, i.e. antibiotics / spam filters 4. So what works effectively today will not be effective tomorrow (antibiotic resistance!). 5. So you have to flag the new metas to the model using signals—user reports, manual classification—and then the model can relabel users.
7 replies
28 recasts
28 reactions
Theleroi.eth
@theleroi
Another question: How does the report system work, and how do we value the different user reports? Can someone behind a big bot-net of bot users spam report a user to trick the algorithm in order to put that reported user under spam label?
1 reply
0 recast
2 reactions
Dan Romero
@dwr.eth
Nope. We have measures to protect against that.
0 reply
1 recast
2 reactions