Strategies for Truth Discovery under Resource Constraints

We present a decision-theory based approach for efficiently sampling information sources in resource-constrained environments, where there is uncertainty regarding source trustworthiness. We exploit diversity among sources to stratify the population into homogeneous subgroups to both minimise redundant sampling and mitigate the effect of certain biases (e.g., source collusion). After presenting our formal framework, we show empirically that our approach performs as well as existing truth discovery approaches with respect to accuracy, while significantly reducing sampling cost.