Tailoring coaching strategies to users’ motivation in a multi-agent health coaching application

The Use of Robots in the Workplace: Conclusions from a Health Promoting Intervention Using Social Robots

Workplace wellness programs constitute a preventive measure to help avoid healthcare costs for companies, with additional benefits for employee productivity and other organizational outcomes. Interventions using social robots may have some advantages over other conventional telemedicine applications, since they can deliver personalized feedback and counseling. This investigation focused on a health-promoting intervention within work environments, and compared the efficacy of the intervention on two distinct groups, one guided by a human agent and the other by a robot agent. Participants (n = 56) were recruited from two Portuguese organizations and led through eight sessions by the social agent, the goal being to encourage health behavior change and adoption of a healthier lifestyle. The results indicate that the group led by the robot agent revealed better post-intervention scores than the group led by the human agent, specifically with regard to productivity despite presenteeism and regard of their level of mental well-being. No effects were found concerning the work engagement level of participants in either group. By demonstrating the potential of using social robots to establish therapeutic and worth relationships with employees in their workplaces, this study provides interesting new findings that contribute to the literature on health behavior change and human-robot interaction.

Effectiveness of Multicomponent Interventions and Physical Activity in the Workplace to Reduce Obesity: A Systematic Review and Meta-Analysis

BACKGROUND

Overweight and obesity are public health problems that affects the workplace. This paper aims to analyse the effectiveness of workplace health promotion interventions in reducing Body Mass Index (BMI); Methods: Following PRISMA guidelines, a systematic review was conducted using PubMed, MEDLINE, and SCOPUS databases. The inverse variance statistical method was used for the meta-analysis with a random effects analysis model and standardised means. The results have been represented by Forest Plots and Funnel Plots graphs; Results: The multicomponent approach had the best results for reducing BMI (-0.14 [-0.24, -0.03], 95% CI; p = 0.009) compared to performing physical activity only (-0.09 [-0.39, 0.21], 95% CI; p = 0.56). However, both methods resulted in positive changes in reducing BMI in the general analysis (-0.12 [-0.22, -0.02], 95% CI; p = 0.01). The GRADE evaluation showed low certainty due to the high heterogeneity between interventions (I² = 59% for overall analysis).

CONCLUSIONS

The multicomponent approach could be an effective intervention to reduce obesity in the working population. However, workplace health promotion programs must be standardised to conduct quality analyses and highlight their importance to workers' well-being.

COVID-BEHAVE dataset: measuring human behaviour during the COVID-19 pandemic

Aiming to illuminate the effects of enforced confinements on people's lives, this paper presents a novel dataset that measures human behaviour holistically and longitudinally during the COVID-19 outbreak. In particular, we conducted a study during the first wave of the lockdown, where 21 healthy subjects from the Netherlands and Greece participated, collecting multimodal raw and processed data from smartphone sensors, activity trackers, and users' responses to digital questionnaires. The study lasted more than two months, although the duration of the data collection varies per participant. The data are publicly available and can be used to model human behaviour in a broad sense as the dataset explores physical, social, emotional, and cognitive domains. The dataset offers an exemplary perspective on a given group of people that could be considered to build new models for investigating behaviour changes as a consequence of the lockdown. Importantly, to our knowledge, this is the first dataset combining passive sensing, experience sampling, and virtual assistants to study human behaviour dynamics in a prolonged lockdown situation.

A randomized trial to promote physical activity in adult pre-hypertensive and hypertensive patients

The purpose of the pilot study was to determine the effectiveness of wearable activity trackers alone or in combination with behaviour change strategies for promoting physical activity (PA) among individuals with pre-hypertension or hypertension. A sample of 44 adults (68% female and mean age 55) were randomized to receive either a Fitbit Charge HR 3 alone (FB) or the Fitbit in combination with behaviour change strategies (i.e., goal setting, behaviour goal review, adaptive feedback) delivered by a trained health coach (FB+) for 12 weeks. Moderate and vigorous PA (MVPA), steps, and sedentary time (ST) were assessed using ActiGraph wGT3X-BT. The FB+ group significantly increased PA [+1854 (2518) steps/day, p < .01] and MVPA [+26 (34) mins/day, p < .05], and decreased their ST [-63 (73) mins/day, p < .01]. The FB group significantly increased  MVPA [+11 (16) mins/day, p < .05], and decreased their ST [-87 (117) mins/day, p < .01]. Participants in FB+ had a significantly greater increase in MVPA/day compared to FB only with a between-group effect size of 0.6 (p < .05). Using Fitbit for self-monitoring is effective in increasing PA and reducing ST among pre-hypertensive and hypertensive participants. Additional behaviour change support amplified the intervention effectiveness for promoting MVPA.

Automatic topic selection for long-term interaction with embodied conversational agents in health coaching: A micro-randomized trial

INTRODUCTION

Embodied Conversational Agents (ECAs) can be included in health coaching applications as virtual coaches. The engagement with these virtual coaches could be improved by presenting users with tailored coaching dialogues. In this article, we investigate if the suggestion of an automatically tailored topic by an ECA leads to higher engagement by the user and thus longer sessions of interaction.

METHODS

A Micro-Randomized Trial (MRT) was conducted in which two types of interaction with an ECA were compared: (a) the coach suggests a relevant topic to discuss, and (b) the coach asks the user to select a topic from a set of options. Every time the user would interact with the ECA, one of those conditions would be randomly selected. Participants interacted in their daily life with the ECA that was part of a multi-agent health coaching application for 4-8 weeks.

RESULTS

In two rounds, 82 participants interacted with the micro-randomized coach a total of 1011 times. Interactions in which the coach took the initiative were found to be of equal length as interactions in which the user was allowed to choose the topic, and the acceptance of topic suggestions was high (71.1% overall, 75.8% for coaching topics).

CONCLUSION

Tailoring coaching conversations with ECAs by letting the coach automatically suggest a topic that is tailored to the user is perceived as a natural variation in the flow of interaction. Future research could focus on improving the novel coaching engine component that supports the topic selection process for these suggestions or on investigating how the amount of initiative and coaching approach by the ECA could be tailored.