People living with dementia are at risk of social isolation, and conversational AI agents can potentially support such individuals by reducing their loneliness. In our study, a conversational AI agent, called MindTalker, co-designed with therapists and utilizing the GPT-4 Large Language Model (LLM), was developed to support people with early-stage dementia, allowing them to experience a new type of “social relationship” that could be extended to real life. Eight PwD engaged with MindTalker for one month or even longer, and data was collected from interviews. Our findings emphasized that participants valued the novelty of AI, but sought more consistent, deeper interactions. They desired a personal touch from AI, while stressing the irreplaceable value of human interactions. The findings underscore the complexities of AI engagement dynamics, where participants commented on the artificial nature of AI, highlighting important insights into the future design of conversational AI for this population.

Navigation systems often aid users when traveling in unfamiliar locations. Current navigation systems tend to focus on identifying the shortest or fastest routes between two points. However, path cost expressed in terms of length and distance (i.e., the utilitarian qualities of travel) is only one attribute which could be used in route recommendation. Recent years have seen navigation systems moving beyond such utilitarian attributes. These include systems aimed at providing users with scenic, safe or attractive routes among other dimensions. In this paper, we contribute to the existing research domain by providing an overview of the different quality-aware route navigation systems that have been proposed in past research for pedestrians. In particular, we examine the different qualities which have been used as key criteria in route recommendation. As the outcome of the paper, we provide a categorization of these systems based on our proposed SWEEP taxonomy. In addition, we outline the various data sources, algorithms and evaluation approaches that have been used to implement quality-aware route navigation systems. Afterwards, we conclude by discussing potential problems encountered in previous studies and highlight promising directions for future research.

Despite the substantial research interest in using Virtual Reality (VR) in healthcare in general and in Psychological, Cognitive, and Behavioral (PC&B) interventions in specific, as well as emerging research supporting the efficacy of VR in healthcare, the design process of translating therapies into VR to meet the needs of critical stakeholders such as users and clinicians is rarely addressed. In this paper, we aim to shed light onto the design needs, opportunities and challenges in designing efficient and effective PC&B-VR interventions. Through analyzing the co-design processes of four user-centered PC&B-VR interventions, we examined how therapies were adapted into VR to meet stakeholders’ requirements, explored design elements for meaningful experiences, and investigated how the understanding of healthcare contexts contribute to the VR intervention design. This paper presents the HCI research community with design opportunities and challenges as well as future directions for PC&B-VR intervention design.

Background: Cognitive Bias Modification of Interpretations (CBM-I) is a computerized intervention designed to change negatively biased interpretations of ambiguous information, which underlie and reinforce anxiety. The repetitive and monotonous features of CBM-I can negatively impact training adherence and learning processes. Objective: This proof-of-concept study aimed to examine whether performing a CBM-I training using mobile virtual reality technology (virtual reality Cognitive Bias Modification of Interpretations [VR-CBM-I]) improves training experience and effectiveness. Methods: A total of 42 students high in trait anxiety completed 1 session of either VR-CBM-I or standard CBM-I training for performance anxiety. Participants’ feelings of immersion and presence, emotional reactivity to a stressor, and changes in interpretation bias and state anxiety, were assessed. Results: The VR-CBM-I resulted in greater feelings of presence (P<.001, d=1.47) and immersion (P<.001, ηp2=0.74) in the training scenarios and outperformed the standard training in effects on state anxiety (P<.001, ηp2=0.3) and emotional reactivity to a stressor (P=.03, ηp2=0.12). Both training varieties successfully increased the endorsement of positive interpretations (P<.001, drepeated measures [drm]=0.79) and decreased negative ones. (P<.001, drm=0.72). In addition, changes in the emotional outcomes were correlated with greater feelings of immersion and presence. Conclusions: This study provided first evidence that (1) the putative working principles underlying CBM-I trainings can be translated into a virtual environment and (2) virtual reality holds promise as a tool to boost the effects of CMB-I training for highly anxious individuals while increasing users’ experience with the training application.