An Unsupervised Bayesian Neural Network for Truth Discovery in Social Networks
This addresses the challenge of truth discovery in social networks without ground truth labels, which is important for applications like misinformation detection, but it appears incremental as it builds on existing autoencoder and Bayesian network techniques.
The paper tackles the problem of estimating event truths from conflicting opinions in social networks by proposing an unsupervised Bayesian neural network that models relationships between truths, agent reliabilities, and social connections, achieving competitive or better performance than state-of-the-art methods on three real datasets.
The problem of estimating event truths from conflicting agent opinions in a social network is investigated. An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations. A Bayesian network model is proposed to guide the learning process by modeling the relationship of the autoencoder's outputs with different variables. At the same time, it also models the social relationships between agents in the network. The proposed approach is unsupervised and is applicable when ground truth labels of events are unavailable. A variational inference method is used to jointly estimate the hidden variables in the Bayesian network and the parameters in the autoencoder. Experiments on three real datasets demonstrate that our proposed approach is competitive with, and in most cases better than, several state-of-the-art benchmark methods.