The goal of this session is to provide a technical framework for building an abusive chat detection system with deep learning. Any system for moderating the communication of an in-game, global community of players will face a number of challenges including how to handle the unique and ever-changing lingo of players, accommodate multiple languages and cultural values simultaneously, and being robust against players trying to circumvent the detection methods. This talk will describe in detail the deep learning architecture and systems level solutions Blizzard chose to tackle these problems.

Takeaway

Attendees will be taught how deep learning algorithms can be used to effectively detect and action disruptive and abusive chat when used in combination with thoughtful system design.

Intended Audience

Engineers, data scientists, and game designers who are interested in building automated systems to detect and penalize abusive and disruptive player behaviors within their games.