Types
Below is a list of all available types that Bodyguard.ai can detect:
HATE_SPEECH- Content that is explicitly violent or discriminatory. This takes the form of racism, LGBTQIA+phobia, misogyny, ableism, dominance, moral or sexual harassment, and threats.
HATEFUL- Content that has malicious intent, including insults, denigration, aggression, condescension, and body-shaming.
UNDESIRABLE- Content that disturbs the experience of followers as well as normal discourse between Internet users.
CRITICISM- Content with a negative tone, but which is not hateful.
NEUTRAL- Content that displays neither supportive nor problematic content.
POSITIVE- Supportive, fairplay, encouraging or body-positive content.
NONE- Belonging to none of the above categories.