1 of 1

Consumers value diverse options when choosing digital mental health support avatars. ��

“I liked that you could choose which one you wanted: �younger, older, man, woman, different races.”�

Non-Cognitive Predictors of Student Success:�A Predictive Validity Comparison Between Domestic and International Students

BACKGROUND

Minority group members often have difficulty finding diverse providers given the current makeup of the mental health work force.
Interventions using digital health agents present the unique potential of offering a variety of diverse agents for consumers to choose from.
This project explored consumer insight around their experience interacting with diverse digital health agents that delivered Motivational Interviewing (MI) for alcohol use.

METHODS

RESULTS

Diversity was mentioned seventy-one times during interviews.
All participants mentioned some aspect of virtual agent diversity including perceived gender (n = 10), perceived ethnicity/race (n = 8), and age (n = 6).
Perceived gender was positively perceived overall (M = 3.44), as was agent ethnicity/race (M = 3.57), and agent age (M = 3.55).
These findings highlight the importance of creating diverse digital health agents that reflect the diversity of consumers that will use them, including a variety of races/ethnicities, ages, and genders.

Demographics

Take a picture to �download the full abstract

PRESENTER:

James Hodgins

Impact of Diverse Virtual Health Agents on Alcohol Users Engaged in a Motivational Interviewing Intervention�Qualitative Analysis of Semi-Structured Interviews

James Hodgins, MA; Jaynish Hazari, MPH, MA; Diane Marin, MA; Christine Lisetti, PhD; Maya Boustani, PhD

Semi-structured interviews

Open coding to identify themes

Organize themes into a codebook

Focused consensus coding

Weigh codes

1: negative 3: neutral 5: positive

N=18

Diversity is viewed positively

“I’m choosing someone that's also female because I feel more comfortable and also someone that is a minority.”

“I picked her because she's …closer to me, as far as maybe ethnicity and maybe age ...”

“His voice sound[ed] urban like he is, … probably black just like me. So that's probably one of the reasons why [I picked him]. He sounded like me.”

Hello there my name is James Hodgins and I am a PhD student in Clinical Psychology working with Dr. Maya Boustani at Loma Linda University in San Bernardino Country, California. Thank you for accessing my poster on the impact of diverse virtual health agents on alcohol users engaged in a motivational interviewing intervention.

Digital health agents have shown potential to provide stand-alone or adjunct behavioral health treatments. Such interventions are more cost-effective, more accessible, and less stigmatizing and therefore may reduce barriers to treatment experienced by many communities. One unique potential of digital health agents is the ability to provide diverse agents for consumers to choose from. This may be especially beneficial for minority groups who often have difficulty finding diverse providers, given the current makeup of the mental health workforce. With this in mind, this project explored consumer insight around their experience interacting with diverse digital health agents during a Motivational Interviewing (MI) intervention for alcohol use.

After engaging with the intervention, individual semi-structured interviews were conducted with eighteen alcohol users. 50% male, 50% female. Largely white but also, African American, Latin/Hispanic, Asian, and Other or Mixed races were represented within the sample. Once interviews were completed, we started with an open coding procedure to identify overall recurring themes which were then organized into a codebook. This codebook was used to focus code all transcripts which were independently coded by two graduate-level psychology students. Lastly, codes were weighted on a scale from 1-5 (1 = negative comment, 3 = neutral mention, 5 = positive statement).

Qualitative data analysis revealed that virtual agent diversity characteristics were perceived positively among alcohol users during this intervention. For example, one participant stated “I like that you could choose which one you wanted - younger, older, man, woman, different races.” All participants mentioned some aspect of virtual agent diversity including 10 participants who mentioned perceived gender (n = 10), 8 mentioned perceived ethnicity/race (n = 8), and 6 mentioned age. As one female minority participant explained, “I'm choosing someone that's also female because I feel more comfortable and also someone that is a minority.”

Further data analysis using weighted averages of codes revealed perceived gender was positively perceived overall (M = 3.7), as was agent ethnicity/race (M = 3.9), and agent age (M = 3.9). Several participants stated they chose a virtual health agent that was like them in at least one diversity characteristic. With one interviewee stating “I guess maybe I picked her because she's … like closer to me, as far as maybe ethnicity and maybe age ...” The decision to choose a digital health agent went beyond just the visual aspects of the avatar as well, with some consumers mentioning aspects of the agent’s given voice. For example, one user stated: “His voice sound[ed] urban like he is, … probably black just like me. So that's probably one of the reasons why [I picked him]. He sounded like me.”

These findings highlight the importance of creating diverse digital health agents that reflect the diversity of consumers that will use them, by including a variety of races/ethnicities, ages, and genders.