Theses Doctoral

Facial expressions as predictors of long-term outcomes following a traumatic event: Comparing automated and manual coding systems

Pfeffer, Charlotte

Human faces provide a rich source of behavioral data. Following acute, potentially traumatic events, manual and automated coding systems of facial behavior may help identify individuals at risk for developing psychopathology. In the present study, OpenFace, an automated system, and FACS, a manual method, were compared as predictors of long-term functioning using facial behavioral data from clinical interviews collected one-month after a potentially traumatic event that brought participants into the emergency department of a Level-1 Trauma Center in New York City. We evaluated similarities and differences in facial emotions identified by FACS and OpenFace to determine their predictive accuracy in capturing Depression and PTSD 6-months and 12-months later. The findings suggest OpenFace is a more sensitive and precise measure of facial behavior than FACS.

Geographic Areas


  • thumnail for Pfeffer_columbia_0054D_18031.pdf Pfeffer_columbia_0054D_18031.pdf application/pdf 2.11 MB Download File

More About This Work

Academic Units
Thesis Advisors
Bonanno, George A.
Ph.D., Columbia University
Published Here
August 9, 2023