Babel Street Analytics API

https://analytics.babelstreet.com/rest/v1/categories

https://raw.githubusercontent.com/rosette-api/curl-examples/develop/examples/categories.curl

Rosette Categorizer analyzes the contents of a string in English and returns the contextual category represented by the string. The possible categories are the Tier 1 contextual categories defined by the IAB Tech Lab Content Taxonomy.

Both single label and multi-label categorization are supported. By default, the categorizer is set to multi-label and returns all relevant category labels with a raw score above a threshold. If no categories exceed the threshold, an empty set is returned.

In addition to a raw score, between negative infinity and infinity, each category label is returned with a confidence score between 0 and 1. The sum of the confidence scores for each category in a given document = 1. The confidence scores reflect the likelihood that a given category label is accurate relative to all other possible category labels. For every document, all twenty-one possible category labels are assigned a confidence score, and the sum of all these scores is one. If multiple labels are relevant to a given document, the confidence scores for each category can be relatively low.

Before analyzing, Categorizer filters out stop words and punctuation, such as “the” “?” “a” “it”, to increase the accuracy of the analysis.

{
  "content": "string",
  "language": "string",
  "options": {  
    "scoreThreshold": -0.25,
    "singleLabel": "false"
  }
}

{
  "categories": [
  {
     "label": "string", 
     "confidence": number,
     "score": number
  }
 ]
}

{
  "supportedLanguages": [
    {
      "language": "string",
      "script": "string",
      "licensed": boolean
    }
  ]
}