An initiative to track and categorise online hateful speech in the Malaysian context using AI (Twitter only for now).
Is hateful speech increasing or decreasing? Which groups are being targeted? Can hate speech monitoring, in Malaysia’s local context, be less manually intensive?
Read more about the initiative here.
Working from the same principles as #Tracker Benci, the Benci Calculator below gauges the likelihood of phrases being hateful, identifies the likely target, and tries to pinpoint the type of hateful speech.
Give it a try. Key in a phrase below.