Unicorn NLP

Language Understanding APIs

Unicorn NLP

Language Understanding APIs

API Documentation (Profanity & Toxicity Detection for User-generated Content)

API Documentation -> Profanity & Toxicity Detection for User-generated Content


Here, we described input/output for Profanity & Toxicity Detection for User-generated Content.

The API is very simple to use and does not require any linguistic or machine learning skills.
API is available via RapidAPI (link), so you need to apply RapidAPI Key that you get after you sign up.

If you have some other questions, need more information, or you need to get the On-Premise version with 0 cents / text (Big Data Compatible) of Profanity & Toxicity Detection for User-generated Content, contact us.


API Documentation for Profanity & Toxicity Detection for User-generated Content

Profanity & Toxicity Detection for User-generated Content API consists of only one endpoint (method) - process. It allows you to process user-generated content (comments, reviews, forums, etc.) and detect toxic and aggressive content (profanity words, toxicity, obscene words, threats, insults, identity hates, and others).

process(title, text) [Endpoint]

Below, you will find the description of each field, both input, and output.


Input (POST):

[Maximum length in total: 5000 characters.]

Example input (POST):

Let's have a look at how this API will process this example text input. Forgive us the language; we are just quoting creative users.


Output (JSON):

This API returns one section: semantic_analysis. It is a result of processing given input with a set of dedicated semantic models regarding toxic and aggressive content (profanity words, toxicity, obscene words, threats, insults, identity hates, and others).

semantic_analysis

Example output:

In this example, 5 semantic models were detected. Each semantic model consist of their id (id_semantic_model), name (name_semantic_model), and a sentence / text segment in which it was detected (segment).
If you have some other questions regarding semantic_analysis output, need more information, or would like to modify semantic models for your needs/your data, contact us.



Example of a JSON API OUTPUT of Profanity & Toxicity Detection for User-generated Content API:

Above, we described each section of the output and displayed it in a more human-friendly form. Below, you will find the format of how our API returns JSON output. The example is the same as above.

Input (POST):

Output (JSON):

Example of a JSON API OUTPUT

{
  "semantic_analysis":{
    "0":{
      "id_semantic_model":2,
      "name_semantic_model":"toxic",
      "segment":"You white idiot"},
    "1":{
      "id_semantic_model":6,
      "name_semantic_model":"insult",
      "segment":"You white idiot"},
    "2":{
      "id_semantic_model":7,
      "name_semantic_model":"identity_hate",
      "segment":"You white idiot"},
    "3":{
      "id_semantic_model":5,
      "name_semantic_model":"threat",
      "segment":"I will find where you live"},
    "4":{
      "id_semantic_model":5,
      "name_semantic_model":"threat",
      "segment":"Beware of the dark"}}
}

What's next

Go to Rapid API and you can start using this API today:

Go to product site to get more description:

Sentiment Analysis 2.0 for Reviews APIs available on Rapid API:



If you have some other questions, need more information, or you need to get the On-Premise version with 0 cents / text (Big Data Compatible) of Sentiment Analysis 2.0 for Reviews, or other Cognitive API for any texts, contact us.