Frameworks that are neither normed nor proportional provide raw, unadjusted scores without benchmarking against a reference population or weighting by relative frequency. Among these, the toxicity framework stands out as the only one that includes ML-based measures, leveraging machine learning to assess language patterns. It's important to note that this framework was trained on social media data, making it particularly useful for analyzing similar contexts, but it may not be applicable to all forms of communication.
Hate speech is a serious and growing problem for online publishers, e-gaming companies, comment moderation platforms, and social media sites. In addition to the ethical reasons for combating online hate speech, governments across the globe are beginning to implement new legislation that requires platforms to remove hateful content within hours or face significant financial penalties.