Statistical Methods for Auditing the Quality of Manual Content Reviews

Xuan Yang, Andrew J Smart, Daniel Theron

Keywords: Content moderation, Audit, Statistical analysis, Human review error

TL;DR: This paper evaluates quantitative methods to measure and to minimize audit risks as a result of human reviews in the form of statistical analysis.

Abstract:

Large technology firms face the problem of moderating content on their online
platforms for compliance with laws and policies. To accomplish this at the scale of
billions of pieces of content per day, a combination of human and machine review
are necessary to label content. Subjective judgement and bias are of concern to
both human annotated content as well as to auditors who may be employed to
evaluate the quality of such annotations in conformance with law and/or policy. To
address this concern, this paper presents a novel application of statistical analysis
methods to identify human error and these sources of audit risk.