Hate speech is currently of broad and current interest in the domain of social media. The anonymity and flexibility afforded by the Internet has made it easy for users to communicate in an aggressive manner. And as the amount of online hate speech is increasing, methods that automatically detect hate speech is very much required.

What it does

It detects hate speech in the work environment (emails, meeting's transcripts -written or recorded-), then creates an immutable report of the incident that will be sent to the HR team (or any organism responsible of dealing with this kind of behavior).

How we built it

An API that uses a ML model to flag hate speech content, in case of a violation the API will create a detailed tamper protected report (a Blockchain database) to the moderator's UI interface. check the attachments for a better understanding.

Share this project: