Using Automated Facial Expression Analysis for Emotion and Behavior Prediction

• In Event: Scholar to Scholar VI

Abstract

We present an overview of facial expressions and emotions and measurement methodologies used in prior studies. Computer models that classify emotions and predict behaviors based on facial expressions can be an effective alternative to human coders. Most predictions can occur based on a small sample of behavior. Empirical studies using the proposed methodology are introduced to demonstrate the use of automated facial expression analysis as a new methodological tool for the investigation of facial expressions.

Authors

• Sun Joo Ahn, Stanford University

• Jeremy Bailenson, Stanford University

• Jesse Fox, Stanford University

• Maria Jabon, Stanford University