Pre-consultation serves as a critical information exchange between healthcare providers and patients, streamlining visits and supporting patient-centered care. Human-led pre-consultations offer many benefits, yet they require significant time and energy from clinical staff. In this work, we identify design goals for pre-consultation chatbots given their potential to carry out human-like conversations and autonomously adapt their line of questioning. We conducted a study with 33 walk-in clinic patients to elicit design considerations for pre-consultation chatbots. Participants were exposed to one of two study conditions: an LLM-powered AI agent and a Wizard-of-Oz agent simulated by medical professionals. Our study found that both conditions were equally well-received and demonstrated comparable conversational capabilities. However, the extent of the follow-up questions and the amount of empathy impacted the chatbot’s perceived thoroughness and sincerity. Patients also highlighted the importance of setting expectations for the chatbot before and after the pre-consultation experience.
19 March 2009 in Foundations and Trends® in Human-Computer Interaction
People may want to recall a multitude of experiences and information from everyday life. Human memory, however, has its limitations and can be insufficient for capturing and allowing access to salient information and important details over time. A variety of tools — primitive, analog, or digital — can complement natural memories through recording. Throughout history, in fact, record keeping and documentation have become increasingly important. In recent years, ubiquitous computing researchers have also designed and constructed mechanisms to support people in gathering, archiving, and retrieving these artifacts, a broad class of applications known as capture and access. In this paper, we overview the history of documentation and recording leading broadly from primitive tools into the current age of ubiquitous computing and automatic or semi-automatic recording technologies. We present historical visions motivating much of the early computing research in this area. We then outline the key problems that have been explored in the last three decades. Additionally, we chart future research directions and potential new focus areas in this space. This paper is based on a comprehensive analysis of the literature and both our experiences and those of many of our colleagues.
20 August 2019 in IEEE Transactions on Visualization and Computer Graphics
Think-aloud protocols are widely used by user experience (UX) practitioners in usability testing to uncover issues in user interface design. It is often arduous to analyze large amounts of recorded think-aloud sessions and few UX practitioners have an opportunity to get a second perspective during their analysis due to time and resource constraints. Inspired by the recent research that shows subtle verbalization and speech patterns tend to occur when users encounter usability problems, we take the first step to design and evaluate an intelligent visual analytics tool that leverages such patterns to identify usability problem encounters and present them to UX practitioners to assist their analysis. We first conducted and recorded think-aloud sessions, and then extracted textual and acoustic features from the recordings and trained machine learning (ML) models to detect problem encounters. Next, we iteratively designed and developed a visual analytics tool, VisTA, which enables dynamic investigation of think-aloud sessions with a timeline visualization of ML predictions and input features. We conducted a between-subjects laboratory study to compare three conditions, i.e., VisTA, VisTASimple (no visualization of the ML's input features), and Baseline (no ML information at all), with 30 UX professionals. The findings show that UX professionals identified more problem encounters when using VisTA than Baseline by leveraging the problem visualization as an overview, anticipations, and anchors as well as the feature visualization as a means to understand what ML considers and omits. Our findings also provide insights into how they treated ML, dealt with (dis)agreement with ML, and reviewed the videos (i.e., play, pause, and rewind).
8 June 2018 in ACM Transactions on Accessible Computing
Although older adults feel generally positive about technologies, many face difficulties when using them and need support during the process. One common form of support is the product instructions that come with devices. Unfortunately, when using them, older adults often feel confused, overwhelmed, or frustrated. In this work, we sought to address the issues that affect older adults’ ability to successfully complete tasks using product instructions. By observing how older adults used the product instructions of various devices and how they made modifications to simplify the use of the instructions, we identified 11 guidelines for creating senior-friendly product instructions. We validated the usability and effectiveness of the guidelines by evaluating how older adults used instruction manuals that were modified to adhere to these guidelines against the originals and those that were modified by interaction design researchers. Results show that, overall, participants had the highest task success rate and lowest task completion time when using guideline-modified user instructions. Participants also perceived these instructions to be the most helpful, the easiest to follow, the most complete, and the most concise among the three. We also compared the guidelines derived from this research to existing documentation guidelines and discussed potential challenges of applying them.
Song signing is a method practiced by people who are d/Deaf and non-d/Deaf individuals to visually represent music and make music accessible through sign language and body movements. Although there is growing interest in song signing, there is a lack of understanding on what d/Deaf people value about song signing and how to make song signing productions that they would consider acceptable. We conducted semi-structured interviews with 12 d/Deaf participants to gain a deeper understanding of what they value in music and song signing. We then interviewed 14 song signers to understand their experiences and processes in creating song signing performances. From this study, we identify three complex, interrelated layers of the song signing creation process and discuss how they can be supported and completed to potentially bridge the cultural divide between the d/Deaf and non-d/Deaf audiences and guide more culturally responsive creation of music.