Detect if the content contains toxic content from a paragraph of text

Question

I am having a HTML textarea where a user enters a descriptive text.
I want to know which service to use (consume) to detect if the user-inputted text is toxic or not.
rekognition/content-moderation and  comprehend seem to be detecting data from media sources like images, videos or PDFs.

Accepted Answer

Comprehend is the best tool for this job.

You will want to create a [Custom Classification](https://docs.aws.amazon.com/comprehend/latest/dg/how-document-classification.html) where you can define words or phrases as "toxic".  Unfortunately it's very hard to determine what constitutes "toxic" language out of the box as everyones definition is slightly different, so this will be the best path.

With Custom Classification, you can define words or phrases and define a label for them to train Comprehend and then run the specific comments through the [Comprehend API](https://docs.aws.amazon.com/comprehend/latest/dg/custom-sync.html) to identify if the text contains any of your custom labels.

Detect if the content contains toxic content from a paragraph of text

관련 콘텐츠