Even Trolls Are Useful: Efficient Link Classification in Signed Networks

TL;DR

This paper introduces a fast, simple, and effective method for classifying links in signed social networks, leveraging psychological insights and applicable in both active and batch settings, with strong empirical validation.

Contribution

It presents a novel, efficient approach for link classification in signed networks, supported by theoretical analysis and superior performance on real-world datasets.

Findings

Algorithms are extremely fast both theoretically and practically.

Methods outperform competitors in accuracy and speed.

Validated on three real-world datasets.

Abstract

We address the problem of classifying the links of signed social networks given their full structural topology. Motivated by a binary user behaviour assumption, which is supported by decades of research in psychology, we develop an efficient and surprisingly simple approach to solve this classification problem. Our methods operate both within the active and batch settings. We demonstrate that the algorithms we developed are extremely fast in both theoretical and practical terms. Within the active setting, we provide a new complexity measure and a rigorous analysis of our methods that hold for arbitrary signed networks. We validate our theoretical claims carrying out a set of experiments on three well known real-world datasets, showing that our methods outperform the competitors while being much faster.