Conference Content

Learn more about who, what, when, and where.
2 of 4
Next

In & Out of the Hub

This is your portal to access more content in the Virtual Hub.
1 of 4
Next

Live Content

On these streams you will find live content happening during the conference.
4 of 4
Close

Connect with others

These spaces are built specifically for you to connect with others at the conference.
3 of 4
Next
← Back to Library
Paper questions
Have a question? Ask a question now and we will try to get it answered during the live Q&A.
Ask a Question?
This paper can be seen in
This live session has already passed 🤭. Luckily there is a recording below.
March
9
Mar 09, 2021
20:00
-
21:45
UTC
Add to Calendar 3/9/21 20:00 3/9/21 21:45 UTC Paper Session 15 Check out this session on the FAccT Hub. https://2021.facctconference.org/conference-agenda/differential-tweetment-mitigating-racial-dialect-bias-in-harmful-tweet-detection
Abstract

Automated systems for detecting harmful social media content are afflicted by a variety of biases, some of which originate in their training datasets. In particular, some systems have been shown to propagate racial dialect bias: they systematically classify content aligned with the African American English (AAE) dialect as harmful at a higher rate than content aligned with White English (WE). This perpetuates prejudice by silencing the Black community. Towards this problem we adapt and apply two existing bias mitigation approaches: preferential sampling pre-processing and adversarial debiasing in-processing. We analyse the impact of our interventions on model performance and propagated bias. We find that when bias mitigation is employed, a high degree of predictive accuracy is maintained relative to baseline, and in many cases bias against AAE in harmful tweet predictions is reduced. However, the specific effects of these interventions on bias and performance vary widely between dataset contexts. This variation suggests the unpredictability of autonomous harmful content detection outside of its development context. We argue that this, and the low performance of these systems at baseline, raise questions about the reliability and role of such systems in high-impact, real-world settings.

Live Q&A Recording
This live session has not been uploaded yet. Check back soon or check out the live session.