AdminMicrosoft Content Moderator Support
(Admin, Microsoft Cognitive Services)
My feedback
-
1 vote
An error occurred while saving the comment -
1 vote
An error occurred while saving the comment Jeff, We are connected via email so I am resolving this thread. As soon as our new update is in production, I will let you know via email.
An error occurred while saving the comment Jeff, We are looking into this in terms of improving the model. An interim workaround would be to use the List Management API to create your custom "allow" or "Block" term lists beyond the default/built-in lists. Will send you the links via email. - Sanjeev
-
1 vote
An error occurred while saving the comment Hello, we are working to resolve this browser caching related bug. The workaround is to clear the cache or use the private/incognito mode and the sign up request should go through.
-
1 vote
An error occurred while saving the comment We recently rolled out the machine-assisted text classification feature (preview) that helps detect potential bullying situations. Please see https://docs.microsoft.com/en-us/azure/cognitive-services/content-moderator/text-moderation-api#classification-preview to get started.
Hi Francois,
What might help your requirement is using the "classify = true" parameter with the API to enable machine-learning based text classification feature on the text, in addition to the term-based profanity filtering.
See https://docs.microsoft.com/en-us/azure/cognitive-services/content-moderator/text-moderation-api#classification
For example, if I used your example word in a sentence as in "You f##kface!", or just "f##kface!" you will see a high offensive score ("Category 3") and the ReviewRecommended flag is set to True.
"Classification": {
"ReviewRecommended": true,
"Category1": {
"Score": 0.068794898688793182
},
"Category2": {
"Score": 0.2296631783246994
},
"Category3": {
"Score": 0.76672351360321045
}
},
Hope this helps.