The Perspective extension uses the Perspective API service for checking comments for spam or toxic content.
The extension supports all available production attributes.
- Parameters names use camelCased attribute names.
- If a specific attribute is not mentioned in the configuration, it won’t be requested from the service.
- A comment will be flagged if any of the thresholds was exceeded.
Consult Perspective docs to learn more about attributes and supported languages.
|Perspective API key|
|Threshold for flagging a rude, disrespectful, or unreasonable comment.||0.5|
|Threshold for flagging a very hateful, aggressive, disrespectful comment.||0.5|
|Threshold for flagging a negative or hateful comment targeting someone because of their identity.||0.5|
|Threshold for flagging an insulting, inflammatory, or negative comment towards a person or a group of people.||0.5|
|Threshold for flagging a comment containing swear words, curse words, or other obscene or profane language.||0.5|
|Threshold for flagging a comment with an intention to inflict pain, injury, or violence against an individual or group.||0.5|