Collective behavior learning by differentiating personal preference from peer influence

Networked data, generated by social media, presents opportunities and challenges to the study of collective behaviors in a social networking environment. In this paper, we focus on multi-label classification on networked data, for which behaviors are represented as labels and an individual can have multiple labels. Existing relational learning methods exploit the connectivity of individuals and they have shown better performance than traditional multi-label classification methods. However, an individual's behavior may be influenced by other factors, particularly personal preference. Hence, we propose a novel approach that integrates causal analysis into multi-label classification to learn collective behaviors. We employ propensity score matching and causal effect estimation to distinguish the contributions of peer influence and personal preference to collective behaviors and incorporate the findings into the design of the classifier. We further study behavior heterogeneity across subgroups in social networks, as people with different demographic features may behave differently due to different impacts of peer influence and personal preference. We estimate conditional average causal effects to analyze the impacts of peer influence and personal preference in different subgroups in social networks. Experiments on real-world datasets demonstrate that our proposed methods improve classification performance over existing methods.