Characterizing Physical Activity in a Health Social Network

Abstract

New horizons are emerging within healthcare delivery, education, intervention provision, and tracking. We study a health social network that has tracked physical activities, biomarkers, and posts the participants have shared, throughout a one-year program. The program was aimed at helping people to adopt healthy behaviors and to lose weight. In this paper, we focus on users' posts that relate to physical activities. Prior papers characterize health based solely on users' information disclosed through natural language or questionnaires. The drawback of these works is their lack of medical records or health-related information to validate their findings. By contrast, with our direct access to users' physical and medical data, we investigate the implication of users' posts at both individual and group levels. We are able to validate our hypotheses about the effects of certain social network activities, by contextualizing them in the specific users' actual medical progress and documented levels of exercise. Our findings show that activity self-disclosure posts are good indicators of one's realworld physical activity, which makes them good resources for monitoring the participants. In addition, using a physical activity propagation model, we show how these posts can influence the physical activity behavior at the network level. Further, posts exhibit distinctive affective, biological, and linguistic style markers. We observe that these characteristics can be used in a predictive capacity, to detect positive activity signals with ∼ 88% accuracy, which can be utilized for an unobtrusive monitoring solution.

Online Actions with Offline Impact

“…Second, we use a comprehensive dataset capturing the introduction and growth of the network and changes in user behavior, allowing us to identify influence effects exactly when new connections are made. With 6 million users recording 631 million activity posts and 160 million days of steps tracking over the course of 5 years, our study is substantially larger than comparable studies on social network effects on physical activity (254 users and 265 posts in [26]). Third, we employ natural experiments [46], difference-in-difference designs [33], and matching procedures [45,48] from the econometrics literature to identify causal relationships from observational data.…”

“…Our analyses exploit these properties to carry out two natural experiments that provide novel insights into how user behavior is shaped by social network interactions. Lastly, the large-scale nature of our dataset-about two million times more posts than previously published research [26]-allows us to study various kinds of heterogeneous effects, for example across age, gender, BMI, previous activity level. Data handling and analysis was conducted in accordance with the guidelines of the appropriate Institutional Review Board.…”

“…More recently, there has been a lot of interest in using social media and online social network datasets as a large-scale sensor into people's activity and health. Studies examined diet and weight loss [24,38,40], mental health [23], and exercise [26]. Other work has used long-term medical studies to study obesity [20] and smoking [21], smart phone and wearable device data to study health benefits of physical activity [5,6], and text messaging data to study mental health [1].…”

“…Therefore, we distinguish between activity posts as a measure of online app engagement and steps taken as a measure of offline physical activity behavior. To the best of our knowledge this is the largest dataset on human activity tracking and social network interactions to date (e.g., ten thousand times more users and a million times more activity tracking than comparable studies [26]).…”