On the Troll-Trust Model for Edge Sign Prediction in Social Networks

TL;DR

This paper analyzes troll-trust heuristics for edge sign prediction in social networks, showing their connection to the Bayes optimal classifier, and proposes scalable algorithms with theoretical guarantees tested on real data.

Contribution

It provides a rigorous analysis linking troll-trust heuristics to probabilistic models and introduces scalable, theoretically grounded algorithms for edge sign prediction.

Findings

The proposed label propagation algorithm is competitive with state-of-the-art methods.

Troll-trust features can be used to develop online learning algorithms with guarantees.

Extensive experiments demonstrate the method's accuracy and scalability.

Abstract

In the problem of edge sign prediction, we are given a directed graph (representing a social network), and our task is to predict the binary labels of the edges (i.e., the positive or negative nature of the social relationships). Many successful heuristics for this problem are based on the troll-trust features, estimating at each node the fraction of outgoing and incoming positive/negative edges. We show that these heuristics can be understood, and rigorously analyzed, as approximators to the Bayes optimal classifier for a simple probabilistic model of the edge labels. We then show that the maximum likelihood estimator for this model approximately corresponds to the predictions of a Label Propagation algorithm run on a transformed version of the original social graph. Extensive experiments on a number of real-world datasets show that this algorithm is competitive against state-of-the-art classifiers in terms of both accuracy and scalability. Finally, we show that troll-trust features can also be used to derive online learning algorithms which have theoretical guarantees even when edges are adversarially labeled.