Skip to main content

Analyses

The API can perform one or more linguistic analyses, which you can configure using the analyses field of the Request object:

  • Language detection: Identifies the dominant language of the document. Our platform currently recognizes over 30 languages.
  • Sentiment analysis: Detects the author's emotional tone in the text. Was the author happy (I loved it.), neutral (We went to London.), or unhappy (The lunch was not good at all.) with their experience? Sentiment is detected at the level of the entire document, individual sentences, and specific entities.
  • Entity recognition: identifies names of persons, companies, dates, etc.
  • Semantic tagging: Returns a set of semantic tags that describe the document's content. Examples of tags include cancel subscription, safe car, or terrible cook.
  • Relations: Detects relations between entities (e.g., cancel(John, subscription)) or between entities and their attributes (e.g., great(pizza)).