Using Social Network Information in Bayesian Truth Discovery

TL;DR

This paper introduces a Bayesian truth discovery framework that leverages social network information and community structures to improve the accuracy of identifying true event states from unreliable agent opinions, especially in sparse data scenarios.

Contribution

It develops novel Laplace and stochastic variational inference methods that incorporate social network communities into truth discovery, enhancing performance over existing approaches.

Findings

Outperforms majority voting and other truth discovery methods in sparse data conditions.

Effectively estimates agent reliabilities and community memberships.

Scales well to large social networks with stochastic inference.

Abstract

We investigate the problem of truth discovery based on opinions from multiple agents who may be unreliable or biased. We consider the case where agents' reliabilities or biases are correlated if they belong to the same community, which defines a group of agents with similar opinions regarding a particular event. An agent can belong to different communities for different events, and these communities are unknown a priori. We incorporate knowledge of the agents' social network in our truth discovery framework and develop Laplace variational inference methods to estimate agents' reliabilities, communities, and the event states. We also develop a stochastic variational inference method to scale our model to large social networks. Simulations and experiments on real data suggest that when observations are sparse, our proposed methods perform better than several other inference methods, including majority voting, TruthFinder, AccuSim, the Confidence-Aware Truth Discovery method, the Bayesian Classifier Combination (BCC) method, and the Community BCC method.