ACM International Conference on Information and Knowledge Management (CIKM) Analysis of Physical Activity Propagation in a Health Social Network Nhathai Phan, Dejing Dou, Xiao Xiao, Brigitte Piniewski, David Kil 1
Outline SMASH Project & Motivation Community - Level Physical Activity Propagation Experimental Results Conclusions & Future Works 2
Obesity & Physical Activity Interventions 18 states (30% = 35%) Medical cost: – $147 billion (in 2008) 30 minutes, 5 days Interventions – Telephone (16) – Website (15) – Effective in short term 3 Prevalence* of Self-Reported Obesity Among U.S. Adults CDC, E.G. Eakin et al C. Vadelanotte et al G.J. Norman et al. 2007
SMASH Project 254 Overweight and Obese individuals with personal information in the YesiWell study Social activities – Online social network, text messages, posts, comments, … – Social games, competitions, … Daily physical activities – Walking, running, jogging, distance, speed, intensity, … Biomarkers, biometric measures – Cholesterol, triglyceride, BMI, … 4
Motivation Utilize social networks to help the physical activity propagation process improve the intervention approaches with affordable cost How can social communications effect the physical activity propagations? – Social interactions – Different granularities – Physical activity propagations & health outcomes 5
Outline SMASH Project & Motivation Community - Level Physical Activity Propagation Experimental Results Conclusions & Future Works 6
……………………. A Trace of Physical Activity Propagation 7 m, t v u [t, t+t w ]
Problem Statement A directed graph – represents an influence relationship – represents the strength of the arc A set of traces 8 K. Saito, R. Nakano, and M. Kimura. Prediction of information diffusion probabilities for independent cascade model. In KES’08, pages Y. Mehmood, N. Barbieri, F. Bonchi, and A. Ukkonen. Csi: Community-level social inuence analysis. In ECML-PKDD’13, pages CPP Model
CPP Model Definition (1) Log likelihood of the traces given Users’ responsibility: 9
CPP Model Definition (2) CPP model learning Probability function is a selection function 10
Learning & Model Selection (1) Complete expectation log likelihood of the observed propagations: Solving We have 11
Learning & Model Selection (2) Users’ responsibilities will not change Run EM algorithm without clustering structure – step 1: estimate – step 2: update Keep fixed, update Bayesian Information Criterion (BIC) 12
Outline SMASH Project & Motivation Community - Level Physical Activity Propagation Experimental Results Conclusions & Future Works 13
Experiment Setting YesiWell dataset – 254 users – Oct 2010 – Aug 2011 BMI value Wellness score Parameter setting: – t w is a day, is a week 14
Detected Communities Influencers: circle nodes Influenced users: rectangle nodes Non-Influenced users: triangle nodes 15
Detected Communities with Health Outcome Measures 16 avg(BMI)avg(WS) avg(#steps)
Consistency of Detected Communities 17 Standard deviation of BMIStandard deviation of WS
CPP vs Social Link, CSI Model Apply optimal clustering on friend network 18 Wellness score #steps
Outline SMASH Project & Motivation Community - Level Physical Activity Propagation Experimental Results Conclusions & Future Works 19
Conclusions and Future Works Propose the CPP model Observations: – Social networks have great potential to propagate physical activities – The propagation network found is almost acyclic – The physical activity-based influence behavior has a strong correlation to health outcome measures (BMI, lifestyles, and Wellness score) Which types of messages are important? Which messages could influence non-influenced users? 20
ACM International Conference on Information and Knowledge Management (CIKM) Thanks you! {haiphan, 21