Study: leading AI models to detect hate speech are 1.5x more likely to flag tweets by African Americans as offensive or hateful, partly due to social context (Shirin Ghaffary/Vox)
Shirin Ghaffary / Vox:
Study: leading AI models to detect hate speech are 1.5x more likely to flag tweets by African Americans as offensive or hateful, partly due to social context — A new study shows that leading AI models are 1.5 times more likely to flag tweets written by African Americans as “offensive” compared to other tweets.
Study: leading AI models to detect hate speech are 1.5x more likely to flag tweets by African Americans as offensive or hateful, partly due to social context (Shirin Ghaffary/Vox)
Source: Tech Meme
