Time-Sensitive Behavior Prediction in a Health Social Network

Human behavior prediction is critical in understanding and addressing large scale health and social issues in online communities. Specifically, predicting when in the future a user will engage in a behavior as opposed to whether a user will behave at a particular time is a less studied subproblem of behavior prediction. Further lacking is exploration of how social context affects personal behavior and the exploitation of network structure information in behavior and time prediction. To address these problems we propose a novel semi-supervised deep learning model for prediction of return time to personal behavior. A carefully designed objective function ensures the model learns good social context embeddings and historical behavior embeddings in order to capture the effects of social influence on personal behavior. Our model is validated on a unique health social network dataset by predicting when users will engage in physical activities. We show our model outperforms relevant time prediction baselines.

[1]  Mingxuan Sun,et al.  A hazard based approach to user return time prediction , 2014, KDD.

[2]  Hao Wang,et al.  Ontology-based deep learning for human behavior prediction in health social networks , 2015, BCB.

[3]  Yelong Shen,et al.  Dynamic socialized Gaussian process models for human behavior prediction in a health social network , 2016, Knowledge and Information Systems.

[4]  Le Song,et al.  Coevolutionary Latent Feature Processes for Continuous-Time User-Item Interactions , 2016, NIPS.

[5]  Nuria Oliver,et al.  Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering , 2010, RecSys '10.

[6]  Jaideep Srivastava,et al.  Just in Time Recommendations: Modeling the Dynamics of Boredom in Activity Streams , 2015, WSDM.

[7]  Masahiro Kimura,et al.  Prediction of Information Diffusion Probabilities for Independent Cascade Model , 2008, KES.

[8]  Utkarsh Upadhyay,et al.  Recurrent Marked Temporal Point Processes: Embedding Event History to Vector , 2016, KDD.

[9]  Damon Centola,et al.  The Spread of Behavior in an Online Social Network Experiment , 2010, Science.

[10]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[11]  Dejing Dou,et al.  Interaction Network Representations for Human Behavior Prediction , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[12]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[13]  Markus Zanker,et al.  Proceedings of the fourth ACM conference on Recommender systems , 2010, RecSys 2010.

[14]  Hugo Larochelle,et al.  An Autoencoder Approach to Learning Bilingual Word Representations , 2014, NIPS.

[15]  Le Song,et al.  Time-Sensitive Recommendation From Recurrent User Activities , 2015, NIPS.

[16]  Hossein Mobahi,et al.  Deep Learning via Semi-supervised Embedding , 2012, Neural Networks: Tricks of the Trade.

[17]  Le Song,et al.  Recurrent Coevolutionary Feature Embedding Processes for Recommendation , 2017, ArXiv.

[18]  N. Christakis,et al.  The Spread of Obesity in a Large Social Network Over 32 Years , 2007, The New England journal of medicine.

[19]  Yehuda Koren,et al.  Collaborative filtering with temporal dynamics , 2009, KDD.