151. Social network structure is predictive of health and wellness
- Author
-
Tomasz Kajdanowicz, Nitesh V. Chawla, Pablo Robles-Granda, Suwen Lin, and Louis Faust
- Subjects
Male ,FOS: Computer and information sciences ,Health Behavior ,Emotions ,Happiness ,Applied psychology ,Social Sciences ,02 engineering and technology ,Social Networking ,0302 clinical medicine ,Sociology ,Heart Rate ,Medicine and Health Sciences ,0202 electrical engineering, electronic engineering, information engineering ,Psychology ,Centrality ,Public and Occupational Health ,Longitudinal Studies ,media_common ,Multidisciplinary ,Social Communication ,Computer Science - Social and Information Networks ,Social Networks ,Health ,Physical Sciences ,Medicine ,Female ,Health behavior ,Behavioral and Social Aspects of Health ,Network Analysis ,Research Article ,Adult ,Computer and Information Sciences ,Adolescent ,Science ,media_common.quotation_subject ,Cardiology ,03 medical and health sciences ,Clustering Coefficients ,020204 information systems ,Mental Health and Psychiatry ,Humans ,Predictability ,Baseline (configuration management) ,Set (psychology) ,Social and Information Networks (cs.SI) ,Structure (mathematical logic) ,Social network ,business.industry ,Biology and Life Sciences ,Communications ,Graph Theory ,business ,Mathematics ,030217 neurology & neurosurgery - 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., Comment: 11 pages, 10 display items(figure and tables)
- Published
- 2019