Incentives for Subjective Evaluations with Private Beliefs

Abstract

The modern web critically depends on aggregation of information from self-interested agents, for example opinion polls, product ratings, or crowdsourcing. We consider a setting where multiple objects (questions, products, tasks) are evaluated by a group of agents. We first construct a minimal peer prediction mechanism that elicits honest evaluations from a homogeneous population of agents with different private beliefs. Second, we show that it is impossible to strictly elicit honest evaluations from a heterogeneous group of agents with different private beliefs. Nevertheless, we provide a modified version of a divergence-based Bayesian Truth Serum that incentivizes agents to report consistently, making truthful reporting a weak equilibrium of the mechanism.

Cite

Text

Radanovic and Faltings. "Incentives for Subjective Evaluations with Private Beliefs." AAAI Conference on Artificial Intelligence, 2015. doi:10.1609/AAAI.V29I1.9311

Markdown

[Radanovic and Faltings. "Incentives for Subjective Evaluations with Private Beliefs." AAAI Conference on Artificial Intelligence, 2015.](https://mlanthology.org/aaai/2015/radanovic2015aaai-incentives/) doi:10.1609/AAAI.V29I1.9311

BibTeX

@inproceedings{radanovic2015aaai-incentives,
  title     = {{Incentives for Subjective Evaluations with Private Beliefs}},
  author    = {Radanovic, Goran and Faltings, Boi},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2015},
  pages     = {1014-1020},
  doi       = {10.1609/AAAI.V29I1.9311},
  url       = {https://mlanthology.org/aaai/2015/radanovic2015aaai-incentives/}
}