JMIR Publications

ABSTRACT

Background:

Access to mental health services continues to pose a global challenge, with current services often unable to meet the growing demand. This has sparked interest in conversational artificial intelligence (AI) agents as potential solutions. Despite this, the development of a reliable virtual therapist remains challenging, and the feasibility of AI fulfilling this sensitive role is still uncertain. One promising approach involves using AI agents for psychological self-talk, particularly within virtual reality (VR) environments. Self-talk in VR allows for externalizing self-conversation by enabling individuals to embody avatars representing themselves as both patient and counselor, thus enhancing cognitive flexibility and problem-solving abilities. However, participants sometimes experience difficulties progressing in sessions, which is where AI could offer guidance and support.

Objective:

This formative study aimed to assess the challenges and advantages of integrating an AI agent into self-talk in VR for psychological counseling.

Methods:

We carried out an iterative design and development of a system and protocol integrating LLMs within VR self-talk. In addition, we conducted an exploratory study in which 11 participants completed a session including: identifying a problem they wanted to address, attempting to address this problem using self-talk in VR, and then continuing self-talk in VR, but this time with the assistance of an LLM-based virtual human. The sessions were carried out with a trained clinical psychologist and were followed by semi-structured interviews. We used qualitative analysis after the interviews to code and develop key themes for the participants that addressed our research objective.

Results:

In total, four themes were identified regarding the quality of advice, the potential advantage of human-AI collaboration in self-help, the believability of the virtual human and other topics. The participants rated 8.3 out of 10 their desire to engage in additional such sessions, and more than half of the respondents indicated that they prefer using VR self-talk with AI rather than without it.

Conclusions:

This exploratory study suggests that the VR self-talk paradigm can be enhanced by LLM-based agents, how exactly to achieve this, potential pitfalls, and additional insights.