Predicting Influential Users in Online Social Networks

TL;DR

This paper investigates how influence models aligned with the dynamic process of information flow in social networks can better predict influential users, demonstrating that non-conservative models like normalized alpha-centrality outperform traditional methods.

Contribution

The study introduces a framework for matching influence models to the underlying dynamic processes, and empirically validates that non-conservative models better predict influential users on Digg.

Findings

Non-conservative influence models outperform conservative ones in predicting influential users.

Normalized alpha-centrality is among the best predictors of influence.

A simple algorithm for computing normalized alpha-centrality is presented.

Abstract

Who are the influential people in an online social network? The answer to this question depends not only on the structure of the network, but also on details of the dynamic processes occurring on it. We classify these processes as conservative and non-conservative. A random walk on a network is an example of a conservative dynamic process, while information spread is non-conservative. The influence models used to rank network nodes can be similarly classified, depending on the dynamic process they implicitly emulate. We claim that in order to correctly rank network nodes, the influence model has to match the details of the dynamic process. We study a real-world network on the social news aggregator Digg, which allows users to post and vote for news stories. We empirically define influence as the number of in-network votes a user's post generates. This influence measure, and the resulting ranking, arises entirely from the dynamics of voting on Digg, which represents non-conservative information flow. We then compare predictions of different influence models with this empirical estimate of influence. The results show that non-conservative models are better able to predict influential users on Digg. We find that normalized alpha-centrality metric turns out to be one of the best predictors of influence. We also present a simple algorithm for computing this metric and the associated mathematical formulation and analytical proofs.