Cutts: Google Webspam Team Used Manual Reviews to Train Future Algorithms
Matt Cutts · Matt Cutts on the US Digital Service and Working at Google for 17 Years · Y Combinator · Dec 4, 2019 · at 17:33
Former head of Google's webspam team Matt Cutts explains how Google systematically fought search spam and structured the feedback loop between human reviewers and automated algorithms.
0:00 / 0:16exact quote · 16.9s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“I, in general, with web spam, the philosophy was do as much as you can with an algorithm. Catch the residual with, you know, manual spam people who are, you know, well trained and extremely good at being able to catch things, and then use that as the training data for the next wave of algorithms.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Matt Cutts
Building dog-walking or weed delivery apps is not saving the world
“Why am I going to go work on Uber for dog walkers? Or how to deliver weed to people better? Which is a, it's a fine problem to work on, but you're not saving the world if you're doing that.”
Cutts: HUD has over 8,000 employees and zero IT staff under 30
“HUD, Housing and Urban Development, has 8000 plus employees. According to the statistics, the number of IT experts, like, there's a job classification, 2210, blah blah blah, we'll just say IT people. The number of IT people under 30 at HUD is zero.”
Cutts: AltaVista would have crushed Google if they grasped ranking signals
“I remember when Alta Vista, I was worried they were going to crush us. Cause like, you know, you have a certain number of ranking signals and if they had twigged and caught on fast enough, they even like copied our appearance.”
Cutts: The SearchKing lawsuit established search results are First Amendment protected
“The result of that lawsuit was that search results are protected by the first amendment.”
Early Google spam moderation lacked the trauma modern content moderators face
“Like Safe Search was just towards pornography, and spam was more like, buy cheap Viagra, and loan consolidation stuff, and so it wasn't nearly as bad as a lot of the content moderators had to deal with.”
Cutts: Fighting spam permanently conditions you to see exploit vectors everywhere
“There is one aspect, though, in which once you've seen all the different ways in which people try to spam and cheat and break the rules, you can't unsee that. Like, it's the black hat mindset. Like, once you realize, hey, here's a thing where people can recycl…”