Predicting the Signs of the Links in a Network

Abstract

It is hard to deny the importance of graph analysis techniques, particularly the problem of link and link-sign prediction, in many real-world applications. Predicting future sign of connections in a network is an important task for online systems such as social networks, e-commerce, scientific research, and others. Several research studies have been presented since the early days of this century to predict either the existence of a link in the future or the property of the link. In this study we present a novel approach that combine both families by using machine learning techniques. Instead of focusing on the established links, we follow a new research approach that focusing on no-link relationship. We aim to understand the move between two states of no-link and link. We evaluate our methods in popular real-world signed networks datasets. We believe that the new approach by understanding the no-link relation has a lot of potential improvement in the future.