Despite HCI research emphasizing the direct involvement of racial minorities in technology design, Black patients have been notably excluded when designing virtual patients intended to represent them in healthcare training applications.To address this gap, this paper describes an iterative user-centered design process to create a virtual patient prototype (EQUITY) that authentically refects realworld racially biased encounters using narratives of Black patients' lived experiences.EQUITY was developed using insights gathered from 6 focus groups with 33 Black patients (Study 1).EQUITY was evaluated with 25 doctors to assess its efectiveness in inducing disorienting experiences and facilitating self-refection (Study 2).Findings suggest that incorporating patient narratives, particularly through virtual patients' verbal and non-verbal behaviors and roleplaying, signifcantly enhanced virtual patient's authenticity and meaningful self-refection among doctors.Our research contributes to HCI by identifying key virtual patient interface design features that align with Black patients' lived experiences of racially biased encounters. CCS Concepts• Human-centered computing → Empirical studies in HCI; • Social and professional topics → Race and ethnicity.

Virtual humans are employed in various contexts, including mental health interventions, to encourage users to adopt healthy behaviors. Establishing rapport with users can enhance the effectiveness of these virtual agents. One way to build rapport is by matching the personality between the virtual human and the participant, which may elicit a similarity-attraction effect, shown to increase trust and likeability in interactions. Despite the potential of computer-generated voices to convey personality through the manipulation of vocalic properties, prior research has primarily focused on non-vocal aspects of personality. To address this gap, we conducted an online study that altered a virtual human's vocalic properties to represent high or low extroversion, with a focus on the role of rapport in promoting mental wellness. In this study, a virtual human provided information on stress-reducing mental-wellness practices to 165 participants. Our findings suggest that synthesizing vocalic properties to resemble a low extroversion level can enhance the persuasiveness of virtual humans and improve rapport, as indicated by participants' self-reported intention to engage in mental-wellness practices.

Counseling requires intimacy between a counselor and a patient to reach healing and growth. However, building rapport between virtual human counselors and computing college students is a complex problem. It requires understanding students' experiences and goals, as also the effects the characteristics of a virtual human counselor, like the spoken accent, have in the interaction with a patient in regards to messenger credibility and self-disclosure. This paper reports findings of how virtual human counselors' spoken accents impact computing undergraduate students' mental wellness conversations in regard to students' self-reported multilingual skills: monolingual or multilingual. We developed two English-speaking rapport-building virtual humans, each with a different spoken English accent-American or German, to interview 62 North American undergraduate computing students from a North American campus. Our findings suggest that virtual humans' spoken accents impacted students' perceptions of the virtual humans' speaking skills. Additionally, we found a similarity-attraction effect between monolingual English speakers and the American-English-accented virtual human counselor concerning participants' engagement and perceptions of the virtual human's speaking skills.

In the context of mental wellness support, trust and intimacy between a counselor and a patient are necessary to converge healing processes positively. However, convincing students to trust a virtual human for topics regarding mental wellness is a complex problem that requires understanding students' experiences. Based on research that discusses mental health as a concerning topic regarding Computer Science (CS) students, this paper investigates how undergraduate computing-related students perceive virtual humans' expertise on mental wellness support based on demographic resemblance on spoken accent and gender. Four virtual human counselors were developed to conduct the study, as 58 undergraduate computing-related students from two North American universities were recruited and assessed. Our findings suggest that students were less inclined to interact with a male virtual human than a female one. Also, that spoken accents can impact students' perceptions of expertise under students' multilingualism.

This paper investigates how a virtual human's persuasion attempts influence the user's intentions to perform the recommended behaviors using the Theory of Planned Behavior. The Theory of Planned Behavior suggests that users' attitudes towards the behavior, subjective norms, and perceived behavior control determine user intentions to perform behaviors. Using the Theory of Planned Behavior, we identify the underlying mechanisms of how users' attitudes, subjective norms, and perceived behavior control influence the effectiveness of virtual human's persuasive attempts on user's intentions to perform the behavior. To identify the underlying mechanisms, we conducted an online study with 202 college students. In a between-subjects study, a virtual human persuaded students to use a mental health coping skill using six different persuasion strategies. We present evidence that persuasion strategies influenced the students' perceived behavior control, which further influenced the user intentions to perform the behavior. Additionally, the paper also shows that user personality influenced the effect of persuasion strategies on students' perceived behavior control. This knowledge of underlying mechanisms of how virtual human's persuasion attempts to influence users' intentions to perform the recommended behavior can help in designing effective intelligent virtual humans for persuasion.

To influence user behaviors, Internet-based virtual humans (VH) have been used to deliver health interventions. However, Internet-based VH health interventions face challenges. The challenges can affect user perceptions of an Internet-based VH health intervention. In our work, we use an Internet-based VH health intervention to promote colorectal cancer (CRC) screening. We present design guidelines drawn from two studies. The two studies examined the influence of visual design and the influence of the information medium on user intentions to pursue more health information. In the first study, the analysis of the focus group (n=73 users) transcripts shows that the VH's visual realism, the VH's healthcare role, and the presence of a local healthcare provider's logo influenced user perceptions of the VH-based intervention's visual design. The findings from the focus groups were used to iterate the intervention and derive design guidelines. In the second study (n=1,400), the analysis of online surveys of users after the VH-based intervention showed that very few users focused on the VH's appearance. To influence the user intentions to pursue the health topic further, the results recommend the use of an animated VH to deliver health information compared to other mediums of information delivery, such as text. The design guidelines from the two studies can be used by developers to use VH-based interventions to influence users' intention to change behaviors.

Anonymous computer-based assessments are used to collect sensitive data in self-report assessments. However they lack human element for building rapport with users. Anonymous rapport building responsive virtual humans (VHs) are known to increase users' willingness to disclose honest information in self-report assessments. However, implementing responsive VHs is a complex task. It requires modeling verbal and nonverbal user behaviors in realtime and generating appropriate responses to address these behaviors. In our work, we investigate the use of non-responsive VHs as middle-ground between computers and responsive VHs to conduct self-report assessments. Prior research has shown that non-responsive VHs, which are unaware of users' behavior, can provide task-related support. We conducted a user study to evaluate the usability of non-responsive VHs to conduct self-report assessment. We also compared users' reported impression management and fear of negative evaluation with computer-based assessment to measure users' willingness to disclose honest information. We found that participants reported significantly higher usability for VH based assessment. Moreover, participants' willingness to disclose honest information with VH was same as in computer-based assessment. We conclude that non-responsive VHs can be used to improve user experience during time consuming self-report assessments.

Virtual humans are used to facilitate interactions in sensitive contexts such as healthcare. In such contexts, trust in the information source plays an important role in reception of the information. Prior work has shown that physical appearance affects trustworthiness in human-human interactions; therefore, we examined the effect of virtual human's appearance on users' trust. We ran a between-users study with 12 adult participants, who watched a video of a virtual human with professional attire (e.g., lab coat) or with general attire (e.g., button-down shirt). We examined the duration of eye fixation on the virtual human's face along with participants' self-reported trust levels. We found that there was no statistical difference in eye contact or trust between the two test conditions.