TurkBench

Abstract

Crowdsourcing is a relatively new model of labor where both the workers and work providers are experiencing its growing pains. A dominant platform that implements this model of labor is Amazon Mechanical Turk (AMT). While AMT has evolved over the years, the changes have focused mainly on work providers and have not addressed the problems workers face (e.g. dealing with market volatility and unpaid time searching for work). In this paper we present TurkBench, a tool meant to provide workers with personalized market visualization and session management. We discuss the design philosophy of the tool, briefly discuss four Turkers' reaction to a demo, and outline future work.

A Data-Driven Analysis of Workers' Earnings on Amazon Mechanical Turk

“…However, encoding this process into a system that can be used by novice workers maximize their wage would be beneficial. Tools that automatically push tasks to workers (e.g., [29,30]) and inform them of how likely the task is to be completable and accepted, combined with real-time information about tasks that exist on the market could thus be useful.…”

Addressing labour exploitation in the data science pipeline: views of precarious US-based crowdworkers on adversarial and co-operative interventions

“…While there are efforts underway to provide technical and regulatory solutions to some identified issues (Hanrahan et al , 2015; Saito et al , 2019; Wang et al , 2022), much of this research involves little if any engagement with workers. A different approach aims to work with crowdworkers to better understand their perspectives and collaboratively design interventions, examples include browser plugins such as Turkopticon (https://turkopticon.net/) and Dynamo (Salehi et al , 2015), and projects such as Fairwork (https://fair.work/en/fw/about) and Fair Crowd Work (http://faircrowd.work/unions-for-crowdworkers/frankfurt-declaration), as well as work that aims to address crowdworkers low participation rates in these kinds of initiatives (Osterbrink and Alpar, 2021).…”

“…While there are efforts underway to provide technical and regulatory solutions to some identified issues (Hanrahan et al, 2015;Saito et al, 2019;Wang et al, 2022), much of this research involves little if any engagement with workers. A different approach aims to work with crowdworkers to better understand their perspectives and collaboratively design interventions, examples include browser plugins such as Turkopticon (https://turkopticon.…”