HBert + BiasCorp -- Fighting Racism on the Web
This work addresses the problem of detecting subtle and overt racism in online content for web developers and users, though it appears incremental in method.
The authors tackled online racism by creating BiasCorp, a dataset of 139,090 comments and news segments from Fox News, BreitbartNews, and YouTube, with 45,000 manually annotated, and developing hBERT, a modified BERT model with Hopfield Layers that reduces complexity and generalizes well across distributions.
Subtle and overt racism is still present both in physical and online communities today and has impacted many lives in different segments of the society. In this short piece of work, we present how we're tackling this societal issue with Natural Language Processing. We are releasing BiasCorp, a dataset containing 139,090 comments and news segment from three specific sources - Fox News, BreitbartNews and YouTube. The first batch (45,000 manually annotated) is ready for publication. We are currently in the final phase of manually labeling the remaining dataset using Amazon Mechanical Turk. BERT has been used widely in several downstream tasks. In this work, we present hBERT, where we modify certain layers of the pretrained BERT model with the new Hopfield Layer. hBert generalizes well across different distributions with the added advantage of a reduced model complexity. We are also releasing a JavaScript library and a Chrome Extension Application, to help developers make use of our trained model in web applications (say chat application) and for users to identify and report racially biased contents on the web respectively.