Assistive Conversational Agent for Health Coaching : a Validation Study
2019-07-05, Fadhil, Ahmed, Wang, Yunlong, Reiterer, Harald
Objectiv: Poor lifestyle represents a health risk factor and is the leading cause of morbidity and chronic conditions. The impact of poor lifestyle can be significantly altered by individual's behavioral modification. Although there are abundant lifestyle promotion applications and tools, they are still limited in providing tailored social support that goes beyond their predefined functionalities. In addition, virtual coaching approaches are still unable to handle user emotional needs. Our approach presents a human-virtual agent mediated system that leverages the conversational agent to handle menial caregiver's works by engaging users (e.g., patients) in a conversation with the conversational agent. The dialog used a natural conversation to interact with users, delivered by the conversational agent and handled with a finite state machine automaton. Our research differs from existing approaches that replace a human coach with a fully automated assistant on user support. The methodology allows users to interact with the technology and access health-related interventions. To assist physicians, the conversational agent gives weighting to user's adherence, based on prior defined conditions.
Materials and Methods: This article describes the design and validation of CoachAI, a conversational agent-assisted health coaching system to support health intervention delivery to individuals or groups. CoachAI instantiates a text-based health care conversational agent system that bridges the remote human coach and the users.
Results: We will discuss our approach and highlight the outcome of a 1-month validation study on physical activity, healthy diet, and stress coping. The study validates technology aspects of our human–virtual agent mediated health coaching system. We present the intervention settings and findings from the study. In addition, we present some user-experience validation results gathered during or after the experimentation.
Conclusions: The study provided a set of dimensions when building a human–conversational agent powered health intervention tool. The results provided interesting insights when using human–conversational agent mediated approach in health coaching systems. The findings revealed that users who were highly engaged were also more adherent to conversational-agent activities. This research made key contributions to the literature on techniques in providing social, yet tailored health coaching support: (1) identifying habitual patterns to understand user preferences; (2) the role of a conversational agent in delivering health promoting microactivities; (3) building the technology while adhering to individuals' daily messaging routine; and (4) a socio-technical system that fits with the role of conversational agent as an assistive component.
Future Work: Future improvements will consider building the activity recommender based on users' interaction data and integrating users' dietary pattern and emotional wellbeing into the initial user clustering by leveraging information and communication technology approaches (e.g., machine learning). We will integrate a sentiment analysis capability to gather further data about individuals and report these data to the caregiver.
Challenges for Brain Data Analysis in VR Environments
2019-04, Jaeger, Sabrina, Klein, Karsten, Joos, Lucas, Zagermann, Johannes, de Ridder, Michael, Kim, Jinman, Yang, Jean, Pfeil, Ulrike, Reiterer, Harald, Schreiber, Falk
Analysing and understanding brain function and disorder is the main focus of neuroscience. Due to the high complexity of the brain, directionality of the signal and changing activity over time, visual exploration and data analysis are difficult. For this reason, a vast amount of research challenges are still unsolved. We explored different challenges of the visual analysis of brain data and the design of corresponding immersive environments in collaboration with experts from the biomedical domain. We built a prototype of an immersive virtual reality environment to explore the design space and to investigate how brain data analysis can be supported by a variety of design choices. Our environment can be used to study the effect of different visualisations and combinations of brain data representation, as for example network layouts, anatomical mapping or time series. As a long-term goal, we aim to aid neuro-scientists in a better understanding of brain function and disorder.
BinocularsVR : A VR experience for the exhibition “From Lake Constance to Africa, a long distance travel with ICARUS”
2019, Sommer, Björn, Feyer, Stefan P., Klinkhammer, Daniel, Klein, Karsten, Wieland, Jonathan, Fink, Daniel, Fiedler, Wolfgang, Flack, Andrea, Nagy, Mate, Wikelski, Martin, Reiterer, Harald, Schreiber, Falk
Outreach and citizen science are important aspects in research and development. For example, the collection of bird-related data is driven forward by non-professional ornithologists as well as by researchers. At the exhibition “From Lake Constance to Africa, a long distance travel with ICARUS” which took place during the summer 2018 at the island Mainau in Germany, a Virtual Reality (VR) installation was shown utilizing movement data of a flock of storks. Two VR binoculars were installed which were used by the visitors to observe storks flying, following their way from Lake Constance towards Africa based on GPS data of real storks. In this way, viewers experienced a 360° view on top of the stork “Bubbel” as it flies with 26 flock mates. The VR binoculars were created as a 3D print equipped with a smartphone, VR headset and other special features enabling the long-term use. The overall project consists of three components: 1) the production software Bird Watcher, 2) the exhibitioncompatible exploration software Bird 360°, as well as 3) the hardware setup: the Sword of Stork Bubbel.
'Too Late to Collaborate' : Challenges to the Discovery of in-Progress Research
2019-06, Breitinger, Corinna, Wortner, Patrick, Gipp, Bela, Reiterer, Harald
Identifying the ongoing research in one's field is an essential yet time-intensive information seeking task. Today's digital libraries support researchers in the search and discovery of published academic research. However, they are unable to support researchers in the discovery of ongoing research, i.e., research that has not yet been published. The discovery of ongoing research thus remains a manual information seeking task lacking standardized processes or automated support systems. We present findings from an initial qualitative study on how computer science researchers from four disciplines currently go about identifying ongoing research projects within their fields and the challenges they face. A major challenge we identify is what we term the discovery-confidentiality trade-off. On the one hand, researchers express a need to discover ongoing research projects in their domain to identify collaboration partners and to avoid performing duplicate research. However, at the same time, researchers are hesitant to reveal details about their own in-progress research for fear of idea plagiarism. We discuss several key factors influencing this trade-off, such as trust and timeliness. We argue that these factors must be accounted for in the design of future academic search and recommendation solutions to support researchers in the timely identification of ongoing research.
Integrating Taxonomies Into Theory-Based Digital Health Interventions for Behavior Change : A Holistic Framework
2019-01-15, Wang, Yunlong, Fadhil, Ahmed, Lange, Jan-Philipp, Reiterer, Harald
Digital health interventions (DHIs) have been emerging in the last decade. Due to their interdisciplinary nature, DHIs are guided and influenced by theories (eg, behavioral theories, behavior change technologies, and persuasive technology) from different research communities. However, DHIs are always coded using various taxonomies and reported in insufficient perspectives. This inconsistency and incomprehensiveness will cause difficulty in conducting systematic reviews and sharing contributions among communities. Therefore, based on existing related work, we propose a holistic framework that embeds behavioral theories, behavior change technique taxonomy, and persuasive system design principles. Including four development steps, two toolboxes, and one workflow, our framework aims to guide DHI developers to design, evaluate, and report their work in a formative and comprehensive way.
The Point-of-Choice Prompt or the Always-On Progress Bar? : A Pilot Study of Reminders for Prolonged Sedentary Behavior Change
2019, Wang, Yunlong, Reiterer, Harald
Prolonged sedentary behavior contributes to many chronic diseases. An appropriate reminder could help screen-based workers to reduce their prolonged sedentary behavior. The fixed-duration point-of-choice prompt has been frequently used in related work. However, this prompting system has several drawbacks. In this paper, we propose the SedentaryBar, a context-aware reminding system using an always-on progress bar to show the duration of a working session, as an alternative to the prompt. The new reminding system uses both users' keyboard/mouse events on the computer and the state-of-the-art computer vision algorithm with the webcam to detect users' presence, which makes the system more accurate and intelligent. Our evaluation study compared the SedentaryBar and the prompt using subjective and objective measurements. After using each method for a week respectively, more participants preferred the SedentaryBar. The participants' perceived interruption and usefulness also suggested the SedentaryBar was more popular during the study. However, the logged data of the participants' working durations indicated the prompt was more effective in reducing their sedentary behavior.
Argus Vision : A Tracking Tool for Exhibition Designers
2019-04-26, Skowronski, Moritz, Klinkhammer, Daniel, Reiterer, Harald
Contemporary exhibitions are increasingly staged using extensive and often interactive media. To create such exhibitions, exhibition design companies employ professionals from a wide range of different disciplines. The support of interdisciplinary exhibition designers in the design process is one goal of research in Human-Computer Interaction. This includes the deployment of Do-It-Yourself (DIY) Tools that enable professionals from all disciplines involved to design and create interactive media themselves. In this paper, we will present Argus Vision, a DIY Tool, which allows exhibition designers the use of camera-tracking to rapidly prototype and develop immersive exhibitions and interactive installations. We successfully used Argus Vision in two real-world case studies both in the prototyping and in the deployment of two installations in exhibitions. Additionally, we conducted expert interviews with exhibition designers, investigating the tool’s usefulness for them.
Learning Patient Transfers with Technology : A Qualitative Investigation of the Design Space
2019, Dürr, Maximilian, Pfeil, Ulrike, Müller, Jens, Borowski, Marcel, Gröschel, Carla, Reiterer, Harald
Nurses who care about patients with functional disabilities are frequently required to transfer a patient from one place to another. To prevent nurses from injuring themselves during patient transfers, many government-supported schools in Germany provide programs which teach how to conduct transfers based on the kinaesthetics care conception. However, the program is typically limited to merely three lectures. With the goal of promoting nurses’ health behavior, we analyzed current practices in kinaesthetics education and explored how interactive technology can extend those practices. We interviewed nursing-care teachers (N = 5) and students (N = 27), and conducted four contextual inquiries during kinaesthetics course sessions. A qualitative analysis of the data revealed three themes. Based on these, we describe a set of implications to support the learning of kinaesthetics-based transfers by means of technology. We propose the use of the implications as initial design goals for user-centered design processes and exemplify their application by illustrating a concept for a tablet-based learning system.
A Qualitative Comparison Between Augmented and Virtual Reality Collaboration with Handheld Devices
2019, Müller, Jens, Zagermann, Johannes, Wieland, Jonathan, Pfeil, Ulrike, Reiterer, Harald
Handheld Augmented Reality (AR) displays offer a see-through option to create the illusion of virtual objects being integrated into the viewer’s physical environment. Some AR display technologies also allow for the deactivation of the see-through option, turning AR tablets into Virtual Reality (VR) devices that integrate the virtual objects into an exclusively virtual environment. Both display configurations are typically available on handheld devices, raising the question of their influence on users’ experience during collaborative activities. In two experiments, we studied how the different display configurations influence user experience, workload, and team performance of co-located and distributed collaborators during a spatial referencing task. A mixed-methods approach revealed that participants’ opinions were polarized towards the two display configurations, regardless of the spatial distribution of collaboration. Based on our findings, we identify critical aspects to be addressed in future research to better understand and support co-located and distributed collaboration using AR and VR displays.