Self-experimentation, or using tracked data to systematically answer health and wellbeing questions via hypothesis testing, has significant potential to support personal health. However, technological support for self-experimentation has focused on expert-designed self-experiments for specific health conditions, limiting people’s ability to design their own rigorous experiments. To address this gap, we developed CASEbot (Conversation Agent for Self-Experimentation), an LLM-powered chatbot using a theory-driven approach to guide users through designing well-structured, personalized, and safe self-experiments. We conducted a within-subjects, mixed-methods study with 42 participants comparing CASEbot to a traditional worksheet-based approach. When formally comparing the experiment rigor and specificity, most participants designed better experiments using CASEbot. They appreciated CASEbot’s conversational approach, which prompted them to surface everyday constraints and proactively raised safety concerns, but some found the platform too rigid in its recommendations. We discuss opportunities for future generative AI self-experimentation systems for health to balance structured guidance with user autonomy.

Journaling plays a crucial role in managing chronic conditions by allowing patients to document symptoms and medication intake, providing essential data for long-term care. While valuable, traditional journaling methods often rely on static, self-directed entries, lacking interactive feedback and real-time guidance. This gap can result in incomplete or imprecise information, limiting its usefulness for effective treatment. To address this gap, we introduce PATRIKA, an AI-enabled prototype designed specifically for people with Parkinson's disease (PwPD). The system incorporates cooperative conversation principles, clinical interview simulations, and personalization to create a more effective and user-friendly journaling experience. Through two user studies with PwPD and iterative refinement of PATRIKA, we demonstrate conversational journaling's significant potential in patient engagement and collecting clinically valuable information. Our results showed that generating probing questions PATRIKA turned journaling into a bi-directional interaction. Additionally, we offer insights for designing journaling systems for healthcare and future directions for promoting sustained journaling.

Conversational agents have gained widespread popularity due to their ability to simulate and sustain contextual conversations. Prior works predominantly focused on computational challenges. However, avatars — the representation of the agent — impact user interactions and perception of conversational agents’ trustworthiness and usefulness. Despite their importance, we lack a holistic understanding of conversational agent avatar design space. In this work, we address this gap by defining a categorization of 10 dimensions that is based on the analysis and iterative coding of 266 conversational agent papers from 160 venues spanning 2003 to the present. In addition, we built an interactive browser to facilitate exploration and interaction with these dimensions and their interrelationships. Our categorization lays the groundwork for researchers, designers, and practitioners to discern task-specific and contextual aspects of conversational agent avatar design. Our work fosters innovative ideas to facilitate new interactions with avatars by surfacing current patterns and highlighting open challenges.

In recent years, the popularity of AI-enabled conversational agents or chatbots has risen as an alternative to traditional online surveys to elicit information from people. However, there is a gap in using single-agent chatbots to converse and gather multi-faceted information across a wide variety of topics. Prior works suggest that single-agent chatbots struggle to understand user intentions and interpret human language during a multi-faceted conversation. In this work, we investigated how multi-agent chatbot systems can be utilized to conduct a multi-faceted conversation across multiple domains. To that end, we conducted a Wizard of Oz study to investigate the design of a multi-agent chatbot for gathering public input across multiple high-level domains and their associated topics. Next, we designed, developed, and evaluated CommunityBots - a multi-agent chatbot platform where each chatbot handles a different domain individually. To manage conversation across multiple topics and chatbots, we proposed a novel Conversation and Topic Management (CTM) mechanism that handles topic-switching and chatbot-switching based on user responses and intentions. We conducted a between-subject study comparing CommunityBots to a single-agent chatbot baseline with 96 crowd workers. The results from our evaluation demonstrate that CommunityBots participants were significantly more engaged, provided higher quality responses, and experienced fewer conversation interruptions while conversing with multiple different chatbots in the same session. We also found that the visual cues integrated with the interface helped the participants better understand the functionalities of the CTM mechanism, which enabled them to perceive changes in textual conversation, leading to better user satisfaction. Based on the empirical insights from our study, we discuss future research avenues for multi-agent chatbot design and its application for rich information elicitation.