Automatic nonverbal behavior indicators of depression and PTSD: the effect of gender

Recently there has been arising interest in automatically recognizing nonverbal behaviors that are linked with psychological conditions. Work in this direction has shown great potential for cases such as depression and post-traumatic stress disorder (PTSD), however most of the times gender differences have not been explored. In this paper, we show that gender plays an important role in the automatic assessment of psychological conditions such as depression and PTSD. We identify a directly interpretable and intuitive set of predictive indicators, selected from three general categories of nonverbal behaviors: affect, expression variability and motor variability. For the analysis, we employ a semi-structured virtual human interview dataset which includes 53 video recorded interactions. Our experiments on automatic classification of psychological conditions show that a gender-dependent approach significantly improves the performance over a gender agnostic one.