The INIT Lab and the Ruiz HCI Lab have been collaborating with Dr. Kathryn Ross in the College of Public Health and Health Professions at UF to investigate research questions about engagement with mHealth apps, long-term use and habituation, and motivation and behavior change, among other avenues. We implemented and published the GatorTrack Android mHealth app that helps users track their weight, food, and activity by displaying the self-monitored data through graphs. The app also sends notifications based on the user’s schedule to engage them.

The World Health Organization defines Mobile Health (mHealth) as the use of mobile and wireless technologies to support the achievement of health objectives. These mobile devices have the potential to deliver health interventions conveniently and at a minimal cost due to their ubiquitous and ever-present nature. Prior work has shown that mHealth apps can support users’ behavioral change towards healthier habits by leveraging various behavior change techniques (BCTs), including goal setting, self-monitoring, prompts (e.g., push notifications), social support, and gamification. In our context, we are interested in how mHealth apps facilitate the user’s self-monitoring of behaviors such as physical activity and health eating to achieve their health goals. Particularly, apps’ push notifications (e.g., reminders for health-related tasks) can increase users’ engagement with the apps and their adherence to health objectives. Therefore, the goal of this project is to explore how mHealth apps can help users achieve their health objective by leveraging push notifications.

As a first step, we explored if there was a gap between notification design recommendations in the literature and practice for mHealth app notifications. We are pleased to share that our paper “A Survey of Notification Designs in Commercial mHealth Apps” was accepted to ACM SIGCHI 2021 as a Late-Breaking Work. Here is our presentation at the CHI 2021 virtual conference. Interested readers can find details of this Late-Breaking Work on its separate study page. Based on the results, our next step is to investigate how the design of notifications, such as notification occurrence and notification content, can affect the user’s engagement with mHealth apps.

Based on the findings from our previous study, we designed a follow-up study to understand how the timing of notifications affects the user’s engagement with mHealth apps. We implemented and published the GatorTrack Android mHealth app that sends context-based push notifications to engage users based on their physical activity transitions detected using machine learning techniques. The app utilizes Google’s Transition API, Firestore database, Firebase Cloud Messaging, and Google Cloud Platform (GCP). I describe this follow-up study in more detail on its separate study page.