Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation

07/09/2021
by   Ian D. Kivlichan, et al.
4

Content moderation is often performed by a collaboration between humans and machine learning models. However, it is not well understood how to design the collaborative process so as to maximize the combined moderator-model system performance. This work presents a rigorous study of this problem, focusing on an approach that incorporates model uncertainty into the collaborative process. First, we introduce principled metrics to describe the performance of the collaborative system under capacity constraints on the human moderator, quantifying how efficiently the combined system utilizes human decisions. Using these metrics, we conduct a large benchmark study evaluating the performance of state-of-the-art uncertainty models under different collaborative review strategies. We find that an uncertainty-based strategy consistently outperforms the widely used strategy based on toxicity scores, and moreover that the choice of review strategy drastically changes the overall system performance. Our results demonstrate the importance of rigorous metrics for understanding and developing effective moderator-model systems for content moderation, as well as the utility of uncertainty estimation in this domain.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/04/2019

A note on 'Collaborative hub location problem under cost uncertainty'

Three models were presented in M.K. Khakim Habibi, Hamid Allaoui, Gilles...
research
08/11/2020

Common Metrics to Benchmark Human-Machine Teams (HMT): A Review

A significant amount of work is invested in human-machine teaming (HMT) ...
research
02/17/2022

Human-Algorithm Collaboration: Achieving Complementarity and Avoiding Unfairness

Much of machine learning research focuses on predictive accuracy: given ...
research
04/25/2022

Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation

Despite impressive performance in many benchmark datasets, AI models can...
research
04/05/2023

Tracing and Visualizing Human-ML/AI Collaborative Processes through Artifacts of Data Work

Automated Machine Learning (AutoML) technology can lower barriers in dat...
research
04/17/2023

Collaborative Bearing Estimation Using Set Membership Methods

We consider the problem of collaborative bearing estimation using a meth...
research
04/28/2020

The more you ask, the less you get: the negative impact of collaborative overload on performance

This paper is about the possible negative impact of excessive collaborat...

Please sign up or login with your details

Forgot password? Click here to reset