Background: The rapid increase of the aging population is pushing many national governments to reshape retirement legislation in order to extend older adults’ working life. Once retired, older adults can be invaluable resources for the community as family carers, as volunteers, or by returning to work. Healthy aging is one of the main conditions for being able to work longer and being active after retirement. The latter, indeed, represents a very sensitive life transition, which can entail psychological and social difficulties. Interventions for promoting older workers’ health and well-being and supporting the transition to retirement are on the top of the policy agenda of most European countries. Recently, computer-based and digital health interventions have been seen as promising means to reach this purpose. Objective: This systematic literature review aimed to explore studies on digital health coaching programs for older workers that followed a user-centered design approach and evaluated their effectiveness in providing older adults with guidance for adopting a healthy lifestyle and being active in the community. Methods: The search identified 1931 papers, and 2 relevant articles were selected by applying specific eligibility criteria. Results: To our knowledge, only few digital health coaching programs have targeted the population of older workers to date; there is an insufficient number of studies on the efficacy of such programs. The results show the difficulties of assessing the efficacy of digital coaching itself and with respect to older employees. The 2 studies suggest that digital health programs for workplaces can improve various aspects of older employees’ well-being; however, they considered health mainly from a physical perspective and neglected contextual, social, psychological, and cultural factors that can influence older workers’ health and general well-being. Future digital health coaching programs should adopt the healthy aging paradigm as a multidimensional lens for interpreting the impact of eHealth technology on aging and retirement. The literature around this issue remains at an embryonic state, and this gap needs to be filled by further investigations that apply a user-centered approach for designing the technology, test innovative research methodologies, and adopt new technical solutions for high-quality interaction design. Conclusions: Further digital health coaching programs aimed at supporting healthy and active living for older workers and retirees are necessary. The user-centered design approach is recommended in order to fully address the users’ health needs and the technological requirements throughout development. Moreover, the healthy aging perspective allows inclusion of physical, social, and psychological factors influencing the transition from work to retirement, as well as the experiences and interactions of individuals with the technology.

Global aging and increasing multimorbidity are questioning the sustainability of healthcare systems. Healthy aging is at the top of the world political agenda, as a possible means for hindering the collapse of care systems. In the aging process, the transition to retirement can lead to an improvement or a deterioration of physical and psychological health. Digital health coaching technology can support older adults at this stage, but what must be the role of such a solution in promoting healthy aging and shaping sustainable care? This qualitative study, carried out in Italy in 2019, involved 15 older workers, retirees, and colleagues. Based on a user-centered design approach, this study aims at gathering older adults’ feelings on a digital health coaching technology for exploring this solution’s potential in promoting healthy aging. Findings highlighted that the digital health coach may help older adults improve several health determinants, e.g., physical activity, cognitive capabilities, and social life, but it can also entail the risk of stigma and break people’s privacy. The latter can be guaranteed by technology customization and codesign. Further research on the digital health coach benefits to boost healthy aging is needed to understand its potential for shaping future sustainable healthcare.

Background: Retirement is recognized as a factor influencing the ageing process. Today, virtual health coaching systems can play a pivotal role in supporting older adults’ active and healthy ageing. This study wants to answer two research questions: (1) What are the user requirements of a virtual coach (VC) based on an Embodied Conversational Agent (ECA) for motivating older adults in transition to retirement to adopt a healthy lifestyle? (2) How could a VC address the active and healthy ageing dimensions, even during COVID-19 times? Methods: Two-wave focus-groups with 60 end-users aged 55 and over and 27 follow-up telephone interviews were carried out in Austria, Italy and the Netherlands in 2019–2020. Qualitative data were analysed by way of framework analysis. Results: End-users suggest the VC should motivate older workers and retirees to practice physical activity, maintain social contacts and emotional well-being. The ECA should be reactive, customizable, expressive, sympathetic, not directive nor patronizing, with a pleasant and motivating language. The COVID-19 outbreak increased the users’ need for functions boosting community relationships and promoting emotional well-being. Conclusions: the VC can address the active and healthy ageing paradigm by increasing the chances of doing low-cost healthy activities at any time and in any place.

Conversational agents are gaining huge popularity in industrial applications such as digital assistants, chatbots, and particularly systems for natural language understanding (NLU). However, a major drawback is the unavailability of a common metric to evaluate the replies against human judgement for conversational agents. In this paper, we develop a benchmark dataset with human annotations and diverse replies that can be used to develop such metric for conversational agents. The paper introduces a high-quality human annotated movie dialogue dataset, HUMOD, that is developed from the Cornell movie dialogues dataset. This new dataset comprises 28,500 human responses from 9500 multi-turn dialogue history-reply pairs. Human responses include: (i) ratings of the dialogue reply in relevance to the dialogue history; and (ii) unique dialogue replies for each dialogue history from the users. Such unique dialogue replies enable researchers in evaluating their models against six unique human responses for each given history. Detailed analysis on how dialogues are structured and human perception on dialogue score in comparison with existing models are also presented.

Retirement is a critical step in older adults’ lives, so it is important to motivate them to stay physically active, mentally healthy, and socially connected in the transition from work to retirement, including through digital health coaching programs. This study aims to: evaluate the impact of a digital coaching intervention to enhance three healthy ageing dimensions, i.e., physical activity, mental well-being, and socialization of a group of adults near retirement; understand the users’ experience; and identify the system strengths and weaknesses. This longitudinal mixed-methods study, carried out in 2021 in Italy and the Netherlands, enrolled 62 individuals. In the first 5 weeks of the trial, participants used a digital coach with the support of human coaches, and then they continued autonomously for another 5 weeks. The use of the digital coach improved the participants’ physical activity, mental well-being and self-efficacy during the first period and only the physical activity in the second. An effective coaching system should be flexible and attractive. High levels of personalization remain the golden key to aligning the health program to the physical, cognitive and social status of the intended target, thus increasing the user-system interaction, usability, and acceptability, as well as enhancing adherence to the intervention.

Background: Living Labs are user-centered, open innovation ecosystems based on a systematic user cocreation approach, which integrates research and innovation processes in real-life communities and settings. The Horizon 2020 Project VITALISE (Virtual Health and Wellbeing Living Lab Infrastructure) unites 19 partners across 11 countries. The project aims to harmonize Living Lab procedures and enable effective and convenient transnational and virtual access to key European health and well-being research infrastructures, which are governed by Living Labs. The VITALISE consortium will conduct joint research activities in the fields included in the care pathway of patients: rehabilitation, transitional care, and everyday living environments for older adults. This protocol focuses on health and well-being research in everyday living environments. Objective: The main aim of this study is to cocreate and test a harmonized research protocol for developing big data–driven hybrid persona, which are hypothetical user archetypes created to represent a user community. In addition, the use and applicability of innovative technologies will be investigated in the context of various everyday living and Living Lab environments. Methods: In phase 1, surveys and structured interviews will be used to identify the most suitable Living Lab methods, tools, and instruments for health-related research among VITALISE project Living Labs (N=10). A series of web-based cocreation workshops and iterative cowriting processes will be applied to define the initial protocols. In phase 2, five small-scale case studies will be conducted to test the cocreated research protocols in various real-life everyday living settings and Living Lab infrastructures. In phase 3, a cross-case analysis grounded on semistructured interviews will be conducted to identify the challenges and benefits of using the proposed research protocols. Furthermore, a series of cocreation workshops and the consensus seeking Delphi study process will be conducted in parallel to cocreate and validate the acceptance of the defined harmonized research protocols among wider Living Lab communities. Results: As of September 30, 2021, project deliverables Ethics and safety manual and Living lab standard version 1 have been submitted to the European Commission review process. The study will be finished by March 2024. Conclusions: The outcome of this research will lead to harmonized procedures and protocols in the context of big data–driven hybrid persona development among health and well-being Living Labs in Europe and beyond. Harmonized protocols enable Living Labs to exploit similar research protocols, devices, hardware, and software for interventions and complex data collection purposes. Economies of scale and improved use of resources will speed up and improve research quality and offer novel possibilities for open data sharing, multidisciplinary research, and comparative studies beyond current practices. Case studies will also provide novel insights for implementing innovative technologies in the context of everyday Living Lab research. International Registered Report Identifier (IRRID): DERR1-10.2196/34567