The third workshop of the series explores how quantitative approaches can shed new light upon, and expand the focus of, qualitative analyses based on annotated corpora of online data. Descriptive quantitative analysis helps us understand the data from a bigger-picture perspective, and allows us to find patterns in how hate speech and its tropes are expressed in online comments sections of mainstream media.
The building of statistical models can also show what factors are driving comments to be classified as hate speech. We will also examine quantitative corpus analysis applied to raw data.
Which quantitative approaches yield the best results in hate speech research? How can these results be used further?