Congrats on the launch! I'm building a comment moderation tool that hides toxic language, profanity and spam on Facebook & Instagram posts and ads. For this tool I'm using Perspective API to score toxicity. Does your service use Perspective API too? Or would it classify our users comments differently compared to their toxicity score?

Report

3yr ago

Welton Wang

ModerateHatespeech

Maker

@paco_vermeulen2 We use our own model actually (it backs our API)! We specifically focused on several weaknesses we identified within Perspective to make it a lot more oriented towards toxicity moderation purposes. We'd love to collaborate with your tool -- wanna shoot me a message?

Report

3yr ago

Paco Vermeulen

@weltonwang absolutely, what's the best way to reach out?

Report

3yr ago

Welton Wang

ModerateHatespeech

Maker

@paco_vermeulen2 my email is welton@moderatehatespeech.com

Report

3yr ago

Biro from Goos.ly

cam.how

@weltonwang we're planning to give this a try for Goosly when we introduce activity comments for public roadmaps. I mentioned ModerateHatespeech in my live stream last evening: