You either die an MVP or live long enough to build content moderation

Post by pier25 » Tue, Sep 28, 2021, 6:02 PM UTC

Alir3z4 wrote: post #60

cowmoo728 wrote: post #35

Earlier quoted context omitted.

I'm interested in why these people were doing this. Were they hoping to get non-tech-savvy people that were searching for computer help? I guess that's a good audience of unwitting users to attempt to hack, but was the goal to get them to submit to one of the remote tech support scams? Were they embedding malware into your blogging platform, or getting ad revenue out of this somehow?

> Were they hoping to get non-tech-savvy people that were searching for computer help? Yes. They would create this posts and get quickly on search results (The platform is pretty good for making SEO optimization out of the box) and they would write good quality posts as well. They would also share this posts on some other websites, especially social media accounts. We don't have Google analytics or such to see where…

Post by User23 » Tue, Sep 28, 2021, 6:03 PM UTC

rtkwe wrote: post #71

It's really funny every time a "we don't censor" platform pops up catering too the American right they speed run going from moderation == censorship to we're moderating our platform in record time. Turns out moderation is really important to make a platform for a community.

Post by falcolas » Tue, Sep 28, 2021, 6:05 PM UTC

infogulch wrote: post #77

Y_Y wrote: post #25

Earlier quoted context omitted.

If your eyes can "normalize" a unusual symbols to a common one to make an English word then so can a lookup table. I feel like this isn't a case where you'd reach first for a neural net.

If you can identify text written with mixed glyphs just ban it outright. Normal users don't use text like this, the pure binary presence of such "homomorphic" text at all is probably a better signal for spam than whatever your neural net when running it after normalization.

Post by airstrike » Tue, Sep 28, 2021, 6:08 PM UTC

wanderingstan wrote: post #64

jffry wrote: post #54

Earlier quoted context omitted.

In fact, the Unicode consortium provides a report and extensive list of "confusable" symbols, which you could use alongside Unicode normalization tables to map adversarial back into more ASCII-equivalent text before running it through anti-spam mechanisms that are interested in the content of the message. https://www.unicode.org/reports/tr39/

I built a Python library for finding strings obfuscated this way. Was critical when moderating our telegram channel before an ICO. https://github.com/wanderingstan/Confusables E.g. "𝓗℮𝐥1೦" would match "Hello"

Post by duxup » Tue, Sep 28, 2021, 6:09 PM UTC

commandlinefan wrote: post #96

duxup wrote: post #68

So true. In HN articles where we discuss social media moderation there's often this idea that "they shouldn't be doing this at all". But I think for most companies and users ... they won't like what a completely moderation free site looks like. So here we are with this painful problem. I kinda wish there was an imaginary "real person with an honest identity" type system that did exist where we could interact without…

> they won't like what a completely moderation free site looks like. So you say, but we've never actually had a chance to see one. We have seen content moderation slippery-slope its way to highly opinionated censorship... every time it's been tried.