Publikationen von Shashank Ahire

As Large Language Models (LLMs) revolutionize Conversational User Interfaces (CUIs) in health and wellbeing, these technologies offer unprecedented potential to enhance user wellbeing by improving physical health, psychological resilience, and social connectivity. However, the integration of such advanced AI into everyday CUI health applications brings substantial challenges, including privacy, user agency, and the psychological impacts of AI interactions. This workshop will provide a platform for collaborative dialogue to explore leveraging these advancements to improve health outcomes while addressing the ethical challenges and risks. Through presentations, breakout sessions, and collaborative discussions, participants will delve into themes such as designing multimodal CUI interventions, structuring conversational interventions for privacy and engagement, personalizing user experiences, and developing proactive and context-adaptive CUI strategies. These discussions aim to develop effective, user-centered CUI strategies that ensure the benefits of LLM-driven innovations are realized without compromising user wellbeing.

Conversational user interfaces (CUIs) have become an everyday technology for people the world over, as well as a booming area of research. Advances in voice synthesis and the emergence of chatbots powered by large language models (LLMs), notably ChatGPT, have pushed CUIs to the forefront of human-computer interaction (HCI) research and practice. Now that these technologies enable an elemental level of usability and user experience (UX), we must turn our attention to higher-order human factors: trust and reliance. In this workshop, we aim to bring together a multidisciplinary group of researchers and practitioners invested in the next phase of CUI design. Through keynotes, presentations, and breakout sessions, we will share our knowledge, identify cutting-edge resources, and fortify an international network of CUI scholars. In particular, we will engage with the complexity of trust and reliance as attitudes and behaviours that emerge when people interact with conversational agents.

In the domain of health and well-being, proactive voice interventions have demonstrated their efficacy. However, users often encounter privacy concerns and social embarrassment due to the lack of control over these proactive interventions, especially in formal and social settings. This study introduces a novel approach called “dual-mode intervention.” It begins with primary interventions using different modalities (like graphical, tactile, or auditory). If users do not respond to these primary interventions, the system delivers voice interventions after a short interval. We conducted a study employing a within-subjects design, which involved 15 participants. The study compared dual-mode interventions with direct voice interventions in office settings, focusing on addressing health and well-being issues. Our findings indicate that knowledge workers preferred dual-mode interventions over direct voice interventions. Moreover, direct voice interventions received significantly lower ratings compared to dual-mode interventions. Also, we identify user preferences for different dual-intervention modalities. Our findings reveal that the user preferences depend on the type of health intervention. Vibration emerged as the preferred modality, followed by graphical output, auditory icons, and ringing interventions.

Prior research has designed and evaluated Voice Assistance (VA) for different settings such as the home, school, and public spaces. Office environments have been relatively understudied, leaving a gap in understanding the essential factors for designing a VA specifically for work settings. In this study, we developed the WorkFit VA specific for the office environment, focusing on the health and well-being of knowledge workers. WorkFit was designed to monitor knowledge workers for sedentary behavior, inconsistent hydration, and stress, and to deliver proactive voice interventions followed by a health recommendation to mitigate those issues. We evaluated WorkFit in a field study with 15 knowledge workers for 5 working days. In the study, we determined challenges and opportunities for voice interactions in work settings. We identified contextual factors for identifying inopportune moments for voice interactions in an office setting. We found that 92\% of knowledge workers accepted WorkFit’s hydration interventions while 79\% of them engaged in walking breaks. Moreover, breathing exercises recommended by WorkFit significantly stabilized the heart rate of knowledge workers during stress. Based on our findings, we propose five design recommendations for the development of VA customized to office settings.

This paper reports on the development of a smart speaker for the home setting of ‘emergent’ users – those whose technology experience and resource availability are low. Earlier research has shown that AI (Artificial Intelligence) powered smart speakers struggled in recognising many emergent users requests. On the other hand, smart speakers powered by human responses were more accurate but slower. In this study, we began by determining, given a choice, emergent users prefer a smart speaker enabled by a human response or an AI response, and what are their preference criteria. We found that they were not completely inclined towards either of those choices. Rather they preferred a smart speaker based on three factors: first, the language of the request, second, the length and complexity of the request, and third, the urgency of response. We developed an integrated version of the smart speaker and evaluated it with emergent user families. From our analysis, it was evident that, when combined, AI and human responses complement each other and provide an elaborate and richer response for emergent users.

Recent research in Human-Computer Interaction for work has shown that conversational agents (CA) are beneficial for supporting focused work and well-being while at work. Knowledge workers struggle in maintaining focus, work schedule, and well-being. Typically, they rely on multiple tools and services for work productivity, scheduling tasks, and reminding breaks. With the goal of tackling these problems, we propose the concept of a ubiquitous work assistant (UWA), which consists of two components: a stationary CA (S-CA) and a wearable CA (W-CA). S-CA is meant to be placed on user’s work desk while W-CA is fixed on the user’s wrist. The UWA interface is distributed between S-CA and W-CA. We initiated our study by conducting semi-structured interviews with knowledge workers (N = 14). We identified their expectations from conversational agents (CAs) that would assist them in their daily work life. From the interview findings, we developed an UWA prototype that could assist users by briefing their daily schedule, monitoring their schedule, and reminding breaks. We conducted a lab study simulating a home-office environment. The findings of the study show that the knowledge workers see potential in the UWA system. Further, we discuss implications of distributed user interface (DUI) for UWA design.

Previous literature has reported that users consider hands-free and eyes-free interaction as one of the prime features of IPAs (Intelligent Personal Assistants). Hands-free and eyes-free interaction enables dual tasking. Although users prefer dual tasking with IPAs, it is unknown to what degree current IPAs are compatible with dual tasking. To determine IPA efficiency while dual tasking, we investigate cognitive load in dual-task scenarios with IPAs. In our experiment, we selected a rhythm game as the primary task and everyday IPA requests as secondary tasks. The secondary tasks belonged to four common categories: information search, multimedia control, smart home control, and turn-taking conversations. The findings show that IPAs need significant improvement to support dual tasking. Out of the four categories, only tasks in the smart home and multimedia categories were appropriate for dual tasking, whereas turn-taking conversation and information search had a high cognitive load. Task completion time was significantly different between tasks, but the penalty on the accuracy of the primary task was small. In interviews we found that, due to information abundance in IPA responses and high time pressure during task completion, users tended to make several mistakes. Based on our findings and observations we derive four design recommendations that facilitate dual-tasking while using IPAs.

In this paper, we aim to draw attention towards wake words. Wake words are an integral part of every request addressed to Intelligent Personal Assistants (IPAs). Currently, a request made to an IPA is led by wake words, making a conversation with an IPA more tiresome than a conversation with a human being. The main question we pose in this paper is, whether we can eliminate the use of wake words at least in specific contexts. Based on our experience with IPAs we propose three less burdensome alternatives that avoid the need for speaking wake words in some cases. Based on these approaches we discuss how to design seamless conversations with IPAs.