Assistive Conversational Agent for Health Coaching: A Validation Study
Assistive Conversational Agent for Health Coaching: A Validation Study
复制标题
DOI：
10.1055/s-0039-1688757
复制
发表时间：
2019-06-01
影响因子：
1.7
通讯作者：
Reiterer, Harald
中科院分区：
文献类型：
--
作者：
Fadhil, Ahmed;Wang, Yunlong;Reiterer, Harald
目的不良的生活方式是一个健康风险因素，是发病率和慢性病的主要原因。不良生活方式的影响可以通过个人行为的改变而显著改变。虽然有大量的生活方式推广应用程序和工具，但它们在提供定制的社会支持方面仍然有限，超出了它们预定义的功能。此外，虚拟教练方法仍然无法处理用户的情感需求。我们的方法提出了一个人类虚拟代理中介系统，利用会话代理通过与会话代理进行对话来吸引用户（例如患者）来处理低级护理人员的工作。对话框使用自然对话与用户交互，由对话代理交付，并由有限状态机自动机处理。我们的研究不同于现有的方法，即用完全自动化的用户支持助手取代人类教练。该方法允许用户与技术互动并获得与健康有关的干预措施。为了帮助医生，会话代理根据先前定义的条件对用户的依从性进行加权。本文描述了CoachAI的设计和验证，CoachAI是一个会话代理辅助健康指导系统，用于支持向个人或团体提供健康干预。CoachAI实例化了一个基于文本的医疗保健会话代理系统，该系统连接了远程人类教练和用户。我们将讨论我们的方法，并强调一项为期1个月的关于身体活动、健康饮食和压力应对的验证研究的结果。该研究验证了我们的人类虚拟代理介导的健康指导系统的技术方面。我们介绍了本研究的干预设置和结果。此外，我们还展示了在实验期间或之后收集的一些用户体验验证结果。该研究为构建人类对话代理驱动的健康干预工具提供了一套维度。当在健康指导系统中使用人类会话代理介导的方法时，结果提供了有趣的见解。研究结果显示，高度参与的用户也更坚持对话代理活动。本研究对提供社会化、量身定制的健康指导支持的技术文献做出了重要贡献：(1)识别习惯模式以了解用户偏好；(2)会话代理在提供健康促进微活动中的作用；(3)在坚持个人日常通讯习惯的同时构建技术；(4)一个社会技术系统，适合对话代理作为辅助组件的角色。未来的改进将考虑基于用户的交互数据构建活动推荐，并通过利用信息和通信技术方法（例如机器学习）将用户的饮食模式和情绪健康整合到初始用户聚类中。我们将整合情感分析功能，以收集有关个人的进一步数据，并将这些数据报告给护理人员。
Objective 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.