The trickster instinctively knowns how to deceive. The problem today is algorithms can be trained to deceive, but instead of the small audience of a con artist, the algorithm is intimately connected to millions of brains trying to make sense of floods of messages.

The objective of this project is to develop a computational model that can be used to estimate the risk of deception in rhetoric. The purpose of this website is to provide an overview of some of the key concepts and share our progress to date.