Search for: All records

There are several barriers to research translation from academia to the broader HCI/UX community and specifically for the design of virtual reality applications. Because of the inaccessibility of evidence-based VR research to industry practitioners, freely-available blog-style media on platforms like Medium, where there is no moderation, is more available, leading to the spread of misinformation. The Design of Virtual Environments (DOVE) website, attempts to address this challenge by offering peer reviewed unbiased VR research, translating it for the layperson, and opening it up to contribution, synthesis and discussion through forums. This paper describes the initial user centered design process for the DOVE website through informal expert interviews, competitive analysis and heuristic review to redesign the site navigation, translation content, and incentivized forms for submission of research. When completed, the DOVE website will aid the translation of AR/VR research to practice. 

Post-traumatic stress disorder (PTSD) is a mental health condition affecting people who experienced a traumatic event. In addition to the clinical diagnostic criteria for PTSD, behavioral changes in voice, language, facial expression and head movement may occur. In this paper, we demonstrate how a machine learning model trained on a general population with self-reported PTSD scores can be used to provide behavioral metrics that could enhance the accuracy of the clinical diagnosis with patients. Both datasets were collected from a clinical interview conducted by a virtual agent (SimSensei) [10]. The clinical data was recorded from PTSD patients, who were victims of sexual assault, undergoing a VR exposure therapy. A recurrent neural network was trained on verbal, visual and vocal features to recognize PTSD, according to self-reported PCL-C scores [4]. We then performed decision fusion to fuse three modalities to recognize PTSD in patients with a clinical diagnosis, achieving an F1-score of 0.85. Our analysis demonstrates that machine-based PTSD assessment with self-reported PTSD scores can generalize across different groups and be deployed to assist diagnosis of PTSD.