single

What really matters—An information gain analysis of questions and reactions in automated PTSD screenings

What really matters—An information gain analysis of questions and reactions in automated PTSD screenings

T. Wörtwein and S. Scherer. What really matters — An information gain analysis of questions and reactions in automated PTSD screenings. In Proceedings of International Conference on Affective Computing and Intelligent Interaction (ACII), 2017

Publications

 

Psychological Distress is a group of overlapping mental disorders which include depression, anxiety, and Post Traumatic Stress Disorder (PTSD). While depressed individuals often lose interest in activities and feel sad or overwhelmed, PTSD is mainly characterized by flashbacks to traumatic events.

We evaluated behaviors of a large group of individuals in interviews with a virtual human. In these interviews, people answered questions related to symptoms of depression and PTSD. During these interactions, we observed more downwards gaze behavior for self-reported depression, a more tense voice for self-reported PTSD and self-reported depression, and less smile intensity for self-reported PTSD. Currently, we focus on automatically estimating behavioral markers which are typically measured by therapists and clinicians.