PokerMetrics: Stress and lie detection through non-invasive physiological sensing

Abstract

In this study, we demonstrate that we can use non-invasive physiology sensing to detect stress and lying, within the context of poker settings. We show how simply derived non-invasive physiological features such as voice pitch variation, skin conductance peaks, and heart rate variability are correlated to a number of high stress situations found in real money no-limit Hold’em tournaments. Using these features, we can develop simple linear models that can be used to identify stress and bluffing.