Virtual humans (i.e., embodied conversational agents) have the potential to support college students’ mental health, particularly in Science, Technology, Engineering, and Mathematics (STEM) fields where students are at a heightened risk of mental disorders such as anxiety and depression. A comprehensive understanding of students, considering their cultural characteristics, experiences, and expectations, is crucial for creating timely and effective virtual human interventions. To this end, we conducted a user study with 481 computer science students from a major university in North America, exploring how they co-designed virtual humans to support mental health conversations for students similar to them . Our findings suggest that computer science students who engage in co-design processes of virtual humans tend to create agents that closely resemble them demographically—agent-designer demographic similarity. Key factors influencing virtual human design included age, gender, ethnicity, and the matching between appearance and voice. We also observed that the demographic characteristics of virtual human designers, especially ethnicity and gender, tend to be associated with those of the virtual humans they designed. Finally, we provide insights concerning the impact of user-designer demographic similarity in virtual humans’ effectiveness in promoting mental health conversations when designers’ characteristics are shared explicitly or implicitly. Understanding how virtual humans’ characteristics serve users’ experiences in mental wellness conversations and the similarity-attraction effects between agents, users, and designers may help tailor virtual humans’ design to enhance their acceptance and increase their counseling effectiveness.

Virtual humans (VHs) have the potential to support mental wellness among college computer science (CS) students. However, designing effective VHs for counseling purposes requires a clear understanding of students’ demographics, backgrounds, and expectations. To this end, we conducted two user studies with 216 CS students from a major university in North America. In the first study, we explored how students co-designed VHs to support mental wellness conversations and found that the VHs’ demographics, appearance, and voice closely resembled the characteristics of their designers. In the second study, we investigated how the interplay between the VH’s appearance and voice impacted the agent’s effectiveness in promoting CS students’ intentions toward gratitude journaling. Our findings suggest that the active participation of CS students in VH design leads to the creation of agents that closely resemble their designers. Moreover, we found that the interplay between the VH’s appearance and voice impacts the agent’s effectiveness in promoting CS students’ intentions toward mental wellness techniques.

Virtual humans demonstrate the ability to act as non-judgmental conversational partners, eliciting greater self-disclosure. However, it is unclear what virtual human and conversational characteristics are important when self-disclosing. To address this gap, we conducted a set of qualitative, semi-formal interviews (n = 17) among computer science students to investigate participant mental models of willingness to disclose to virtual humans and characteristics of virtual humans that affect their self-disclosure. Our findings indicate that participants' mental models of virtual humans are largely inconsistent with current literature. This inconsistency appears to eliciting hesitancy and discomfort with virtual humans. Furthermore, trust and listening were identified as two primary characteristics of a virtual human interaction that are valuable towards willingness to disclose. Additionally, these characteristics were also valued in different ways for virtual humans in comparison to real humans. From the interviews, we identify and provide guidelines of designing virtual human interactions and conversations to elicit greater willingness to disclose.

Simulating real-world experiences in a safe environment has made virtual human medical simulations a common use case for research and interpersonal communication training. Despite the benefits virtual human medical simulations provide, previous work suggests that users struggle to notice when virtual humans make potentially life-threatening verbal communication mistakes inside virtual human medical simulations. In this work, we performed a 2x2 mixed design user study that had learners (n = 80) attempt to identify verbal communication mistakes made by a virtual human acting as a nurse in a virtual desktop environment. A virtual desktop environment was used instead of a head-mounted virtual reality environment due to Covid-19 limitations. The virtual desktop environment experience allowed us to explore how frequently learners identify verbal communication mistakes in virtual human medical simulations and how perceptions of credibility, reliability, and trustworthiness in the virtual human affect learner error recognition rates. We found that learners struggle to identify infrequent virtual human verbal communication mistakes. Additionally, learners with lower initial trustworthiness ratings are more likely to overlook potentially life-threatening mistakes, and virtual human mistakes temporarily lower learner credibility, reliability, and trustworthiness ratings of virtual humans. From these findings, we provide insights on improving virtual human medical simulation design. Developers can use these insights to design virtual simulations for error identification training using virtual humans.