Stefan Scherer: “Automatic Behavior Descriptors for Psychological Disorder Analysis”

April 25, 2013 | Shanghai, China

Speaker: Stefan Scherer
Host: FG 2013

Abstract: We investigate the capabilities of automatic nonverbal behavior descriptors to identify indicators of psychological disorders such as depression, anxiety, and post-traumatic stress disorder (PTSD). We seek to confirm and enrich present state of the art, predominantly based on qualitative manual annotations, with automatic quantitative behavior descriptors. We propose four nonverbal behavior descriptors that can be automatically estimated from visual signals. We introduce a new dataset called the Distress Assessment Interview Corpus (DAIC) which includes 167 dyadic interactions between a confederate interviewer and a paid participant. Our evaluation on this dataset shows correlation of our automatic behavior descriptors with specific psychological disorders as well as a generic distress measure. Our analysis also includes a deeper study of self-adaptor and fidgeting behaviors based on detailed annotations of where these behaviors occur.

In particular, we identify three main findings: (1) There are significant differences in the automatically estimated gaze behavior of subjects with psychological disorders. In particular, an increased overall downwards angle of the gaze could be automatically identified using two separate automatic measurements, for both the face as well as the eye gaze; (2) using automatic measurements, we could identify on average significantly less intense smiles for subjects with psychological disorders as well as significantly shorter average durations of smiles; (3) based on the manual analysis, subjects with psychological conditions exhibit on average longer self-touches and fidget on average longer with both hands (e.g. rubbing, stroking) and legs (e.g. tapping, shaking).