Node Classification in Social Networks

TL;DR

This paper surveys various techniques for classifying nodes in large social network graphs, focusing on iterative classifiers and label propagation methods, and discusses their similarities, extensions, and future directions.

Contribution

It provides a comprehensive overview of existing node classification methods, unifying different approaches under a common perspective and highlighting their similarities and potential extensions.

Findings

Identifies two main categories: iterative classifiers and label propagation methods.

Highlights the common principles underlying different classification approaches.

Discusses extensions and future research directions in node classification.

Abstract

When dealing with large graphs, such as those that arise in the context of online social networks, a subset of nodes may be labeled. These labels can indicate demographic values, interest, beliefs or other characteristics of the nodes (users). A core problem is to use this information to extend the labeling so that all nodes are assigned a label (or labels). In this chapter, we survey classification techniques that have been proposed for this problem. We consider two broad categories: methods based on iterative application of traditional classifiers using graph information as features, and methods which propagate the existing labels via random walks. We adopt a common perspective on these methods to highlight the similarities between different approaches within and across the two categories. We also describe some extensions and related directions to the central problem of node classification.