Trends in Persuasive Technologies for Physical Activity and Sedentary Behavior: A Systematic Review

A panoramic view of personalization based on individual differences in persuasive and behavior change interventions

Persuasive technologies are designed to change human behavior or attitude using various persuasive strategies. Recent years have witnessed increasing evidence of the need to personalize and adapt persuasive interventions to various users and contextual factors because a persuasive strategy that works for one individual may rather demotivate others. As a result, several research studies have been conducted to investigate how to effectively personalize persuasive technologies. As research in this direction is gaining increasing attention, it becomes essential to conduct a systematic review to provide an overview of the current trends, challenges, approaches used for developing personalized persuasive technologies, and opportunities for future research in the area. To fill this need, we investigate approaches to personalize persuasive interventions by understanding user-related factors considered when personalizing persuasive technologies. Particularly, we conducted a systematic review of 72 research published in the last ten years in personalized and adaptive persuasive systems. The reviewed papers were evaluated based on different aspects, including metadata (e.g., year of publication and venue), technology, personalization dimension, personalization approaches, target outcome, individual differences, theories and scales, and evaluation approaches. Our results show (1) increased attention toward personalizing persuasive interventions, (2) personality trait is the most popular dimension of individual differences considered by existing research when tailoring their persuasive and behavior change systems, (3) students are among the most commonly targeted audience, and (4) education, health, and physical activity are the most considered domains in the surveyed papers. Based on our results, the paper provides insights and prospective future research directions.

A theory-based and data-driven approach to promoting physical activity through message-based interventions

Objective

We investigated how physical activity can be effectively promoted with a message-based intervention, by combining the explanatory power of theory-based structural equation modeling with the predictive power of data-driven artificial intelligence.

Methods

A sample of 564 participants took part in a two-week message intervention via a mobile app. We measured participants' regulatory focus, attitude, perceived behavioral control, social norm, and intention to engage in physical activity. We then randomly assigned participants to four message conditions (gain, non-loss, non-gain, loss). After the intervention ended, we measured emotions triggered by the messages, involvement, deep processing, and any change in intention to engage in physical activity.

Results

Data analysis confirmed the soundness of our theory-based structural equation model (SEM) and how the emotions triggered by the messages mediated the influence of regulatory focus on involvement, deep processing of the messages, and intention. We then developed a Dynamic Bayesian Network (DBN) that incorporated the SEM model and the message frame intervention as a structural backbone to obtain the best combination of in-sample explanatory power and out-of-sample predictive power. Using a Deep Reinforcement Learning (DRL) approach, we then developed an automated, fast-profiling strategy to quickly select the best message strategy, based on the characteristics of each potential respondent. Finally, the fast-profiling method was integrated into an AI-based chatbot.

Conclusion

Combining the explanatory power of theory-driven structural equation modeling with the predictive power of data-driven artificial intelligence is a promising strategy to effectively promote physical activity with message-based interventions.

Beyond "Exercise as Medicine" in Physical Therapy: Toward the Promotion of Exercise as a Public Good

Physical therapists are uniquely positioned through their knowledge and skills to help people become more physically active, which may reduce the consequences of physical inactivity for health-related quality of life and the global economy. The "Exercise Is Medicine" campaign was introduced in 2007. It holds that exercise may be prescribed like a medicine. Although this analogy doubtlessly has promoted innumerable life-changing conversations between clinicians and patients, there are important shortcomings to considering physical activity and exercise as medicine. In the United States, many of these shortcomings relate to how medical services are provided and remunerated. Medical care is provided in the context of exclusive groups, which are established by insurance, preferred service populations, or other characteristics that determine a basis for providing care. Exclusivity means that medical care is frequently provided in a type of club. The club structure of medical care jeopardizes the ability of nonmembers to benefit. Medical care clubs based on payment create an environment in which nonpaying customers may not benefit in the same manner as paying customers from approaches that consider exercise prescribed as medicine. This clinical perspective reviews the characteristics of exercise as a good, focusing on how it is prescribed by physical therapists. It discusses how physical therapists may become involved in the process of making exercise a public good by reducing its exclusivity. Multiple levels of involvement are recommended at the societal, community, and individual levels. These involvements may be guided by an existing construct proposed by the World Health Organization, which would bring the global physical therapy profession into a common alignment. This Perspective concludes with a discussion that anticipates the shortcomings of conceptualizing exercise as a public good to be addressed in future service delivery models.

Investigating psychological variables for technologies promoting physical activity

Background

Many technological interventions designed to promote physical activity (PA) have limited efficacy and appear to lack important factors that could increase engagement. This may be due to a discrepancy between research conducted in this space, and software designers' and developers' use of this research to inform new digital applications.

Objectives

This study aimed to identify (1) what are the variables that act as barriers and facilitators to PA and (2) which PA variables are currently considered in the design of technologies promoting PA including psychological, physical, and personal/contextual ones which are critical in promoting PA. We emphasize psychological variables in this work because of their sparse and often simplistic integration in digital applications for PA.

Methods

We conducted two systematized reviews on PA variables, using PsycInfo and Association for Computing Machinery Digital Libraries for objectives 1 and 2.

Results

We identified 38 PA variables (mostly psychological ones) including barriers/facilitators in the literature. 17 of those variables were considered when developing digital applications for PA. Only few studies evaluate PA levels in relation to these variables. The same barriers are reported for all weight groups, though some barriers are stronger in people with obesity.

Conclusions

We identify PA variables and illustrate the lack of consideration of these in the design of PA technologies. Digital applications to promote PA may have limited efficacy if they do not address variables acting as facilitators or barriers to participation in PA, and that are important to people representing a range of body weight characteristics.

Correlations between Physical Fitness and Body Composition among Boys Aged 14–18—Conclusions of a Case Study to Reverse the Worsening Secular Trend in Fitness among Urban Youth Due to Sedentary Lifestyles

A secular trend can be observed throughout the world with an increase in childhood obesity and a decrease in fitness. The research aimed to examine the results of tests measuring the conditional abilities of young boys aged 14–18 in fitness tests and their correlations with body composition indicators. That was supported by research that has been prepared in Hungary so far. This research focuses on the results of fitness tests conducted on 14- to 18-year-old boys, presented along with body composition data. The authors sought to describe the development of the fitness profiles of males at a Budapest secondary school participating in the research, based on the results of the Hungarian National Student Fitness Test (NETFIT®), and also how their physical characteristics affect the results of NETFIT® tests in the sample measured. A total of 735 male high school students at a Budapest secondary school (14–18 years old) (mean ± SD, 16.05 ± 1.18 years) participated in the survey. The data were collected in the 2018/2019 academic year, and it was compared with the national data. The correlation between the performance indicators of the NETFIT® tests and the physical characteristic indicators was analyzed using the two-block Partial Least Squares method. In the resulting groups, Kruskal–Wallis variance analysis was performed to investigate the differences in performance. In contrast, pairs of group differences were tested with the Mann–Whitney test. Boys with a short physique were at some advantage in trunk-lifts and push-ups, compared to taller boys. It was also obvious that being overweight is a hindrance regarding the PACER test or the standing broad jump. The handgrip in the left and right hand was mostly of similar strength or weakness. Tall-heavy children performed better in this test. The grip strength of tall-thin students was also strong, but not as strong as in the tall-heavy group. Reducing the percentage of body fat (PBF) and creating the optimal BMI index is important for the younger age group, as our results have clearly demonstrated that overweight is a hindrance in the PACER, VO2 max, standing broad jump, back-saver sit-and-reach, and push-up tests.

Personality-targeted persuasive gamified systems: exploring the impact of application domain on the effectiveness of behaviour change strategies

Persuasive gamified systems for health are interventions that promote behaviour change using various persuasive strategies. While research has shown that these strategies are effective at motivating behaviour change, there is little knowledge on whether and how the effectiveness of these strategies vary across multiple domains for people of distinct personality traits. To bridge this gap, we conducted a quantitative study with 568 participants to investigate (a) whether the effectiveness of the persuasive strategies implemented vary within each domain (b) whether the effectiveness of various strategies vary across two distinct domains, (c) how people belonging to different personality traits respond to these strategies, and (d) if people high in a personality trait would be influenced by a persuasive strategy within one domain and not in the other. Our results show that there are significant differences in the effectiveness of various strategies across domains and that people's personality plays a significant role in the perceived persuasiveness of different strategies both within and across distinct domains. The Reward strategy (which involves incentivizing users for achieving specific milestones towards the desired behaviour) and the Competition strategy (which involves allowing users to compete with each other to perform the desired behaviour) were effective for promoting healthy eating but not for smoking cessation for people high in Conscientiousness. We provide design suggestions for developing persuasive gamified interventions for health targeting distinct domains and tailored to individuals depending on their personalities.

Intra-Company Crowdsensing: Datafication with Human-in-the-Loop

Every day employees learn about things happening in their company. This includes plain facts witnessed while on the job, related or not to one’s job responsibilities. Many of these facts, which we call “occurrence data”, are known by employees but remain unknown to the company. We suppose that some of them are valuable and may improve the company’s situational awareness. In the spirit of mobile crowdsensing, we propose intra-company crowdsensing (ICC), a method of “extracting” occurrence data from employees. In ICC, an employee occasionally responds to sensing requests, each about one plain fact. We elaborate the concept of ICC, proposing a model of human-system interaction, a system architecture, and an organizational process. We position ICC with respect to related concepts from information technology, and we look at it from selected organizational and managerial viewpoints. Finally, we conducted a survey, in which we presented the concept of ICC to employees of different companies and asked for their evaluation. Respondents positive about ICC outnumbered skeptics by a wide margin. The survey also revealed some concerns, mostly related to ICC being perceived as another employee surveillance tool. However, useful and acceptable sensing requests are likely to be found in every organization.

Health Issues Due to the Global Prevalence of Sedentariness and Recommendations towards Achieving a Healthier Behaviour

Sedentariness has progressed in recent years. Here, we summarize the high prevalence of objectively measured sedentariness and the list of health problems associated with sedentariness. According to the literature, a minimum sedentary time of 8 h/d may avoid the harmful effects of sedentariness. Our review of the literature shows that many countries worldwide exceed this threshold. The coronavirus disease 2019 pandemic has increased the proportion of time spent seated in chairs and/or other types of furniture. Furthermore, prolonged sedentariness will continue to increase because it is assumed that people, at least those in desk jobs, perform their work better when sitting than when standing. Many practical solutions should be implemented to help people reduce their sedentary time. People need to be aware that prolonged sedentariness causes health problems. They need to measure the amount of time spent being sedentary to self-guide their behaviour. They should adopt a new lifestyle to avoid prolonged sedentariness and prolonged standing. In addition, we point out that they should frequently change their posture to avoid fatigue and health issues. For global public health, there is an urgent need to adopt an intermediate healthy/healthier behaviour between too much time spent in the sitting and standing positions.

Connecting Social Psychology and Deep Reinforcement Learning: A Probabilistic Predictor on the Intention to Do Home-Based Physical Activity After Message Exposure

Previous research has shown that sending personalized messages consistent with the recipient's psychological profile is essential to activate the change toward a healthy lifestyle. In this paper we present an example of how artificial intelligence can support psychology in this process, illustrating the development of a probabilistic predictor in the form of a Dynamic Bayesian Network (DBN). The predictor regards the change in the intention to do home-based physical activity after message exposure. The data used to construct the predictor are those of a study on the effects of framing in communication to promote physical activity at home during the Covid-19 lockdown. The theoretical reference is that of psychosocial research on the effects of framing, according to which similar communicative contents formulated in different ways can be differently effective depending on the characteristics of the recipient. Study participants completed a first questionnaire aimed at measuring the psychosocial dimensions involved in doing physical activity at home. Next, they read recommendation messages formulated with one of four different frames (gain, non-loss, non-gain, and loss). Finally, they completed a second questionnaire measuring their perception of the messages and again the intention to exercise at home. The collected data were analyzed to elicit a DBN, i.e., a probabilistic structure representing the interrelationships between all the dimensions considered in the study. The adopted procedure was aimed to achieve a good balance between explainability and predictivity. The elicited DBN was found to be consistent with the psychosocial theories assumed as reference and able to predict the effectiveness of the different messages starting from the relevant psychosocial dimensions of the recipients. In the next steps of our project, the DBN will form the basis for the training of a Deep Reinforcement Learning (DRL) system for the synthesis of automatic interaction strategies. In turn, the DRL system will train a Deep Neural Network (DNN) that will guide the online interaction process. The discussion focuses on the advantages of the proposed procedure in terms of interpretability and effectiveness.

Effect of an education-based workplace intervention (move in office with education) on sedentary behaviour and well-being in desk-based workers: a cluster randomized controlled trial

This study aimed to assess the effectiveness of short-term workplace-based physical activity education on altering sitting outcomes, maximal oxygen consumption (V_O2max) and occupational well-being. Four office clusters (46 participants) of desk-based workers were randomized to either the move in office with education (MOWE) group or the control (CONT) group for 4 weeks. The outcomes were occupational sedentary time, V_O2max and workplace well-being. Data were analysed using non-parametric tests. Our study results did not show any significant change in sitting time or V_O2max. Nevertheless, workplace well-being of the MOWE group significantly improved when compared to the CONT group, especially in the domains of work satisfaction (odds ratio 11.67; p = 0.001) and employer care (odds ratio 0.167; p = 0.001). Workplace education (MOWE) improves well-being but may not alter sitting outcomes or V_O2max in office workers. Workplace education without policy change may not yield positive health outcomes.