Reputation Agent: Tools to Help Digital Workers Earn More and Create Fairer Workspaces

Lead PI

Abstract

Gig markets rely on reviews to help customers or employers identify the workers they want to hire. However, gig markets have been plagued with unfair assessments containing inaccurate reputation signals about workers which can not only limit workers’ future job opportunities, but can also result in workers not getting paid or even being terminated from the marketplace. Unfair reviews are generally created because employers have a hard time differentiating the factors within the workers’ control and the ones that have little to do with their performance (e.g., when they complain about an Uber driver getting stuck in traffic). However, because market power is typically placed in the hands of employers, a bad worker review can result in the worker losing her entire livelihood.

To address this problem, we present Reputation Agent, a review validation system that helps employers to generate fair reviews. Reputation Agent implements an intelligent interface that: (1) uses deep learning to automatically detect when an individual has included unfair factors into her review (factors that are outside the control of the gig worker, according to the policies of the market); and (2) prompts the individual to reconsider her review if she has incorporated unfair factors. Reputation Agent, in contrast with traditional approaches, motivates customers and employers to review gig workers’ performance more fairly. We discuss how tools that bring more transparency to employers about the policies of a gig market can help build empathy, spark discussions around the established gig market rules, and could be used to help platform maintainers identify potential injustices towards workers generated by their interfaces. Our vision is that with truth and transparency we can bring fairer treatment of gig workers.

To learn more, visit the Reputation Agent project page.

Funding

NSF

Related Publications