Virtual Human Questionnaire for Analysis of Depression, Anxiety and Personality

Shashank Jaiswal, Michel F. Valstar, Keerthy Kusumam, Chris Greenhalgh

Abstract: Self-report questionnaires like PHQ-9 and GAD-7 are often used in the field of psychology to detect mental health problems and measure their severity. Their validity has been well established by a number of previous studies. However, most previous studies have used self-administration method to study their validity. In the context of automating the administering of questionnaires as a part of an interaction scenario led by a virtual human, we investigate if the virtual human administration of these questionnaires can be considered equivalent to the self-administration of these questionnaires (through an electronic form). Additionally, we also examine the equivalence when the virtual human is replaced by a real human. The interaction with real human is studied in two different modes: face-to-face and through a video-conferencing link. Statistical analysis of the scores obtained from our user study (consisting of 55 participants) revealed that human/virtual-human administered questionnaires can be considered practically equivalent to self administered ones. In most cases, the differences in the scores from self-administered questionnaires and human/virtual-human administered questionnaires, were found to be smaller than any effect size which could be considered practically significant.