Incentives for Subjective Evaluations with Private Beliefs

Authors

  • Goran Radanovic Ecole Polytechnique Fédérale de Lausanne (EPFL)
  • Boi Faltings Ecole Polytechnique Fédérale de Lausanne (EPFL)

DOI:

https://doi.org/10.1609/aaai.v29i1.9311

Keywords:

Mechanism Design, Information Elicitation, Peer Prediction

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.

Downloads

Published

2015-02-16

How to Cite

Radanovic, G., & Faltings, B. (2015). Incentives for Subjective Evaluations with Private Beliefs. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). https://doi.org/10.1609/aaai.v29i1.9311

Issue

Section

AAAI Technical Track: Game Theory and Economic Paradigms