How AI Can Help Identify & Moderate Harmful Content

1 min read
Emily R.
Emily R.
Published May 5, 2022 Updated May 23, 2022

Machine Learning Engineer Chiara Caratelli covers how Natural Language Processing (NLP) technology can be leveraged to identify and moderate commercial spam at DeveloperWeek Europe 2022.

Whether you’re attending a virtual event or watching your favorite gamer on a live stream, communicating via chat is a great way to engage with fellow participants, the host, and the content itself. But, bad actors, bots, and trolls can take advantage of the instantaneous nature of live chat, lower the trust and safety rating of your platform, and ruin the experience for everyone.

Luckily, artificial intelligence (AI) solutions exist to help human moderators review a high volume of messages so that harmful content never even has a chance to reach innocent chat users.

Chiara Caratelli covers some of the advanced techniques used to develop AI-driven chat moderation that even the craftiest of spammers cannot circumvent.

Learn more about in-app messaging with Stream by activating your free, 30-day chat trial.

decorative lines
Integrating Video With Your App?
We've built an audio and video solution just for you. Launch in days with our new APIs & SDKs!
Check out the BETA!