Virtual Human Interviewers May Help Armed Services Members Open Up About PTSD Interview with:

Dr. Gale Lucas, PhD Director of Research USC Institute for Creative Technologies Playa Vista, CA 

Dr. Lucas

Dr. Gale Lucas, PhD
Director of Research
USC Institute for Creative Technologies
Playa Vista, CA What is the background for this study? What are the main findings?

Response: A common barrier to healthcare for psychiatric conditions is the stigma associated with these disorders. Perceived stigma prevents many from reporting their symptoms. Stigma is a particularly pervasive problem among military service members, preventing them from reporting symptoms of combat-related conditions like posttraumatic stress disorder (PTSD).

This put them at risk for having their symptoms go untreated, with possible disastrous outcomes including suicide attempts. We envisioned a technology system – a virtual human interviewer – whereby military service members can get feedback about their risk for PTSD in a safe place without stigma. Indeed, our prior research has shown that, because its “just a computer” (therefore safe and anonymous), this virtual human interviewer helps people to feel safe discussing sensitive issues like mental health symptoms. In this follow-up research project (published in Frontiers), we sought to demonstrate the value of this kind of virtual human interviewer specifically for encouraging reporting of PTSD symptoms among service members.

Specifically, we were interested in comparing the willingness of service members to report symptoms of PTSD to our virtual human interviewer, compared to the gold standard of the Post Deployment Health Assessment (PDHA). We wanted to isolate the effect of anonymity, separating it from “relational factors” that the virtual human interviewer uses to encourage service members to open up. Indeed, before asking these same questions as on the PDHA to capture PTSD symptoms, the system engages in social dialogue, which build rapport with users. The system asks “get to know you questions,” and throughout the interview, engage in active listening with responses such as nods, smiles, saying “uh huh,” and other encouraging phrases like “that’s great.”

To study the impact of these relational behaviors separately from anonymity, we included an anonymous version of the PDHA in addition to our virtual human interviewer and the official PDHA. Compared to both the official (non-anonymous) PDHA and anonymous PDHA, our virtual human interviewer encouraged significantly greater reporting of PTSD symptoms. That is, the service members were more willing to report symptoms of PTSD to the virtual human interviewer, which was both anonymous and used relational behaviors, compared to the anonymous PDHA (which was only anonymous but was just a checklist without relational exchange with the participant) and the official PDHA (which was neither anonymous nor relational). What should readers take away from your report?

Response: Armed Services could potentially employ systems like our virtual human interviewer, which are both anonymous and help service members to open up using relational exchange. These kinds of technologies could be used to provide service members a safe way to get feedback about their risks for PTSD.  This research suggests there could be a benefit of putting virtual human interviewers in VA locations, for the use of our service members who are transitioning back to civilian life. Additionally, providing access to these kinds of technology to service members returning from deployment could serve as an important adjunct to the PDHA. This could help members who are unwilling to report symptoms of PTSD on the PDHA. By receiving anonymous feedback from the virtual human interviewer that they are at risk for PTSD, they could be encouraged to seek help without having their symptoms flagged on their military record. Is there anything else you would like to add?

Response: Previous research with our virtual interviewer (Lucas, Gratch, King & Morency, 2014) has compared human interviewers and virtual interviewers. Compared with a human interviewer the virtual interviewer provides users with anonymity, which could help soldiers to reveal more about their mental health symptoms. In contrast to this previous work, the current research looks at anonymity in terms of the difference between official PDHA (which goes on their record) versus the other two formats (anonymous PDHA and virtual interviewer, which are both anonymous). Then by comparing anonymous PDHA and virtual interviewer, we can see the effect of building rapport separately from anonymity (because both of these are anonymous, but virtual human interviewers build rapport with users whereas the PDHA checklist cannot). Thank you for your contribution to the community.


Gale M. Lucas, Albert Rizzo, Jonathan Gratch, Stefan Scherer, Giota Stratou, Jill Boberg, Louis-Philippe Morency. Reporting Mental Health Symptoms: Breaking Down Barriers to Care with Virtual Human Interviewers. Frontiers in Robotics and AI, 2017; 4 DOI: 10.3389/frobt.2017.00051

Note: Content is Not intended as medical advice. Please consult your health care provider regarding your specific medical condition and questions. 

[wysija_form id=”1″]






Last Updated on October 17, 2017 by Marie Benz MD FAAD