Social Network Structure is Predictive of Health and Wellness

TL;DR

This paper demonstrates that the structure of social networks can significantly improve the prediction of individual health and wellness states beyond traditional demographic and physical data.

Contribution

The authors introduce the NetCARE model, which uses social network topology features to enhance health and wellness state predictions.

Findings

NetCARE improves prediction accuracy by up to 65%.

Network structure features add significant predictive value.

Model tested on large longitudinal student data.

Abstract

Social networks influence health-related behaviors, such as obesity and smoking. While researchers have studied social networks as a driver for diffusion of influences and behaviors, it is less understood how the structure or topology of the network, in itself, impacts an individual's health behaviors and wellness state. In this paper, we investigate whether the structure or topology of a social network offers additional insight and predictability on an individual's health and wellness. We develop a model called the Network-Driven health predictor (NetCARE) that leverages features representative of social network structure. Using a large longitudinal data set of students enrolled in the NetHealth study at the University of Notre Dame, we show that the NetCARE model improves the overall prediction performance over the baseline models -- that use demographics and physical attributes -- by 38%, 65%, 55%, and 54% for the wellness states -- stress, happiness, positive attitude, and self-assessed health -- considered in this paper.