Sequential Multi-Class Labeling in Crowdsourcing

TL;DR

This paper introduces a sequential questioning strategy for multi-class labeling in crowdsourcing, optimizing question design based on previous responses to improve accuracy within budget constraints.

Contribution

It develops a POMDP-based framework and a Ulam-Rényi game approach for adaptive question sequencing, enhancing label accuracy over non-sequential methods.

Findings

Our methods outperform non-sequential error correction strategies.

The Ulam-Rényi based approach improves labeling accuracy.

Sequential questioning reduces the number of responses needed.

Abstract

We consider a crowdsourcing platform where workers' responses to questions posed by a crowdsourcer are used to determine the hidden state of a multi-class labeling problem. As workers may be unreliable, we propose to perform sequential questioning in which the questions posed to the workers are designed based on previous questions and answers. We propose a Partially-Observable Markov Decision Process (POMDP) framework to determine the best questioning strategy, subject to the crowdsourcer's budget constraint. As this POMDP formulation is in general intractable, we develop a suboptimal approach based on a $q$-ary Ulam-R\'enyi game. We also propose a sampling heuristic, which can be used in tandem with standard POMDP solvers, using our Ulam-R\'enyi strategy. We demonstrate through simulations that our approaches outperform a non-sequential strategy based on error correction coding and which does not utilize workers' previous responses.