Paper Info
Title
A Temporally Heterogeneous Survival Framework with Application to Social Behavior Dynamics
Abstract
Social behavior dynamics is one of the central building blocks in understanding and modeling complex social dynamic phenomena, such as information spreading, opinion formation, and social mobilization. While a wide range of models for social behavior dynamics have been proposed in recent years, the essential ingredients and the minimum model for social behavior dynamics is still largely unanswered. Here, we find that human interaction behavior dynamics exhibit rich complexities over the response time dimension and natural time dimension by exploring a large scale social communication dataset. To tackle this challenge, we develop a temporal Heterogeneous Survival framework where the regularities in response time dimension and natural time dimension can be organically integrated. We apply our model in two online social communication datasets. Our model can successfully regenerate the interaction patterns in the social communication datasets, and the results demonstrate that the proposed method can significantly outperform other state-of-the-art baselines. Meanwhile, the learnt parameters and discovered statistical regularities can lead to multiple potential applications.
Year
DOI
Venue
2017
10.1145/3097983.3098189
KDD
Keywords
Field
DocType
Social Dynamics,temporally Heterogeneous Survival framework,Human Behaviors
Data mining,Opinion formation,Computer science,Baseline (configuration management),Response time,Social communication,Human interaction,Human behavior,Artificial intelligence,Social dynamics,Multiple time dimensions,Machine learning
Conference
ISBN
Citations 
PageRank 
978-1-4503-4887-4
4
0.40
References 
Authors
23
5
Name
Order
Citations
PageRank
Linyun Yu11024.83
Peng Cui22317110.00
Chaoming Song358023.58
Tianyang Zhang4574.35
Shiqiang Yang52478155.24