Analysing Ego-Networks via Typed-Edge Graphlets: A Case Study of Chronic Pain Patients

Graphlets, being the fundamental building blocks, are essential for understanding and analysing complex networks. The original notion of graphlets, however, is unable to encode edge attributes in many types of networks, especially in egocentric social networks. In this paper, we introduce a framework to embed edge type information in graphlets and generate a Typed-Edge Graphlets Degree Vector (TyE-GDV). Through applying the proposed method to a case study of chronic pain patients, we find that not only a patient's social network structure could inform his/her perceived pain grade, but also particular types of social relationships, such as friends, colleagues and healthcare workers, are more important in understanding the effect of chronic pain. Further, we demonstrate that including TyE-GDV as additional features leads to significant improvement in a typical machine learning task.