Explore the capabilities and limitations of AI in detecting online hate speech in this 58-minute talk from the Alan Turing Institute. Delve into the research of Paul Röttger and Bertie Vidgen as they discuss their work on HateCheck, a suite of tests designed to evaluate hate speech detection models. Gain insights into the potential of AI to reduce the burden on human content moderators and understand the complexities involved in automated hate speech detection. Examine the strengths and weaknesses of current AI technologies in tackling this challenging aspect of online content moderation.
Overview
Syllabus
How good is AI at detecting online hate?
Taught by
Alan Turing Institute