TY - JOUR
T1 - Dynamic socialized Gaussian process models for human behavior prediction in a health social network
AU - Shen, Yelong
AU - Phan, Nhat Hai
AU - Xiao, Xiao
AU - Jin, Ruoming
AU - Sun, Junfeng
AU - Piniewski, Brigitte
AU - Kil, David
AU - Dou, Dejing
N1 - Funding Information:
This work is supported by the NIH grant R01GM103309. The authors appreciate the anonymous reviewers for their extensive and informative comments to help improve the paper. The authors also appreciate the contribution of Nafisa Chowdhury.
Publisher Copyright:
© 2015, Springer-Verlag London.
PY - 2016/11/1
Y1 - 2016/11/1
N2 - Modeling and predicting human behaviors, such as the level and intensity of physical activity, is a key to preventing the cascade of obesity and helping spread healthy behaviors in a social network. In our conference paper, we have developed a social influence model, named socialized Gaussian process (SGP), for socialized human behavior modeling. Instead of explicitly modeling social influence as individuals’ behaviors influenced by their friends’ previous behaviors, SGP models the dynamic social correlation as the result of social influence. The SGP model naturally incorporates personal behavior factor and social correlation factor (i.e., the homophily principle: Friends tend to perform similar behaviors) into a unified model. And it models the social influence factor (i.e., an individual’s behavior can be affected by his/her friends) implicitly in dynamic social correlation schemes. The detailed experimental evaluation has shown the SGP model achieves better prediction accuracy compared with most of baseline methods. However, a Socialized Random Forest model may perform better at the beginning compared with the SGP model. One of the main reasons is the dynamic social correlation function is purely based on the users’ sequential behaviors without considering other physical activity-related features. To address this issue, we further propose a novel “multi-feature SGP model” (mfSGP) which improves the SGP model by using multiple physical activity-related features in the dynamic social correlation learning. Extensive experimental results illustrate that the mfSGP model clearly outperforms all other models in terms of prediction accuracy and running time.
AB - Modeling and predicting human behaviors, such as the level and intensity of physical activity, is a key to preventing the cascade of obesity and helping spread healthy behaviors in a social network. In our conference paper, we have developed a social influence model, named socialized Gaussian process (SGP), for socialized human behavior modeling. Instead of explicitly modeling social influence as individuals’ behaviors influenced by their friends’ previous behaviors, SGP models the dynamic social correlation as the result of social influence. The SGP model naturally incorporates personal behavior factor and social correlation factor (i.e., the homophily principle: Friends tend to perform similar behaviors) into a unified model. And it models the social influence factor (i.e., an individual’s behavior can be affected by his/her friends) implicitly in dynamic social correlation schemes. The detailed experimental evaluation has shown the SGP model achieves better prediction accuracy compared with most of baseline methods. However, a Socialized Random Forest model may perform better at the beginning compared with the SGP model. One of the main reasons is the dynamic social correlation function is purely based on the users’ sequential behaviors without considering other physical activity-related features. To address this issue, we further propose a novel “multi-feature SGP model” (mfSGP) which improves the SGP model by using multiple physical activity-related features in the dynamic social correlation learning. Extensive experimental results illustrate that the mfSGP model clearly outperforms all other models in terms of prediction accuracy and running time.
KW - Dynamic social correlation
KW - Health social network
KW - Socialized Gaussian process
UR - http://www.scopus.com/inward/record.url?scp=84952641922&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84952641922&partnerID=8YFLogxK
U2 - 10.1007/s10115-015-0910-z
DO - 10.1007/s10115-015-0910-z
M3 - Article
AN - SCOPUS:84952641922
SN - 0219-1377
VL - 49
SP - 455
EP - 479
JO - Knowledge and Information Systems
JF - Knowledge and Information Systems
IS - 2
ER -