Theory-based habit modeling for enhancing behavior prediction in behavior change support systems.

Psychological theories of habit posit that when a strong habit is formed through behavioral repetition, it can trigger behavior automatically in the same environment. Given the reciprocal relationship between habit and behavior, changing lifestyle behaviors is largely a task of breaking old habits and creating new and healthy ones. Thus, representing users' habit strengths can be very useful for behavior change support systems, for example, to predict behavior or to decide when an intervention reaches its intended effect. However, habit strength is not directly observable and existing self-report measures are taxing for users. In this paper, building on recent computational models of habit formation, we propose a method to enable intelligent systems to compute habit strength based on observable behavior. The hypothesized advantage of using computed habit strength for behavior prediction was tested using data from two intervention studies on dental behavior change ( N = 36 and N = 75 ), where we instructed participants to brush their teeth twice a day for three weeks and monitored their behaviors using accelerometers. The results showed that for the task of predicting future brushing behavior, the theory-based model that computed habit strength achieved an accuracy of 68.6% (Study 1) and 76.1% (Study 2), which outperformed the model that relied on self-reported behavioral determinants but showed no advantage over models that relied on past behavior. We discuss the implications of our results for research on behavior change support systems and habit formation.

Habit and goal-related constructs in determining toothbrushing behavior: Two sensor-based longitudinal studies.

OBJECTIVES: Two longitudinal studies were conducted to examine how habits and goal-related constructs determine toothbrushing behavior from a dual-process perspective. We aimed to describe the variations of habit strength, intention, and attitude and to test their associations with actual behavior at both inter- and intraindividual levels. In addition, toothbrushing behavior was measured both by self-report and sensors with the goal to compare these measures. METHOD: In Study 1, 40 young adults were instructed to brush their teeth twice a day, and their behaviors were measured by accelerometers for 3 weeks. Participants also self-reported their instrumental and affective attitude, habit strength, and behavior frequency weekly. Effects of interest were estimated using structural equation modeling. Study 2 replicated Study 1 with a larger and more diverse sample (N = 79), adding a measure of behavioral intention. RESULTS: Supporting the dual-process account, habit strength predicted future behavior in addition to goal-related constructs. Habit strength also attenuated the influences of goal-related constructs on behavior, but this pattern only emerged interindividually and for self-reported behavior. In addition, toothbrushing behavior was more strongly driven by affective rather than instrumental attitude. In both studies, associations among variables were weaker within-person and when sensor-measured behavior was modeled. CONCLUSIONS: The partial support for the dual-process account suggests the need of using habit-based interventions to complement intention-based interventions when attempting to change oral health routines. Our findings also highlight the importance of affective aspects of toothbrushing behavior and the potential to incorporate sensor-based objective measures in research and interventions. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Intelligent mobile support for therapy adherence and behavior change.

Mobile applications have proven to be promising tools for supporting people in adhering to their health goals. Although coaching and reminder apps abound, few of them are based on established theories of behavior change. In the present work, a behavior change support system is presented that uses a computational model based on multiple psychological theories of behavior change. The system determines the user's reason for non-adherence using a mobile phone app and an online lifestyle diary. The user automatically receives generated messages with persuasive, tailored content. The system was designed to support chronic patients with type 2 diabetes, HIV, and cardiovascular disease, but can be applied to many health and lifestyle domains. The main focus of this work is the development of the model and the underlying reasoning method. Furthermore, the implementation of the system and some preliminary results of its functioning will be discussed.