Amazon Comprehend

Amazon Comprehend uses natural language processing (NLP) to extract insights about the content of documents. Amazon Comprehend processes any text file in UTF-8 format. It develops insights by recognizing the entities, key phrases, language, sentiments, and other common elements in a document. Use Amazon Comprehend to create new products based on understanding the structure of documents. For example, using Amazon Comprehend you can search social networking feeds for mentions of products or scan an entire document repository for key phrases.

Cloud CMS features out-of-the-box integration with Amazon Comprehend to provide the following services:

  • Entity Detection - Amazon Comprehend returns a list of entities, such as people, places, and locations, identified in a document.
  • Key Phrases - Amazon Comprehend extracts key phrases that appear in a document. For example, a document about a basketball game might return the names of the teams, the name of the venue, and the final score.
  • Language - Amazon Comprehend identifies the dominant language in a document. Amazon Comprehend can identify 100 languages.
  • Sentiment - Amazon Comprehend determines the emotional sentiment of a document. Sentiment can be positive, neutral, negative, or mixed.

Entity Detection

Add the f:aws-entities feature to a content type or a single content instance to have Amazon Comprehend's Entity Detection services automatically pick out entities from your content's JSON and binary attachments.

With this feature in place, your content will be automatically analyzed and updated in the background as changes are made by your editorial team.

To learn more, check out AWS Entities Detection.

Key Phrase Detection

Add the f:aws-keyphrases feature to a content type (or a single content instance) to have Amazon Comprehend's Key Phrase Detection services automatically find any key phrases from within your content's JSON or binary attachments.

With this feature in place, your content will be automatically analyzed and updated in the background as changes are made by your editorial team.

To learn more, check out AWS Keyphrases Detection.

Dominant Language Detection

Add the f:aws-dominant-language feature to a content type (or a single content instance) to have Amazon Comprehend's Dominant Language Detection services automatically analyze your content's JSON and binary attachments to determine the dominant language locale.

The locale is stored back onto your content using the f:locale feature, making it fully compatible with I18N and multilingual content within Cloud CMS.

With this feature in place, your content will be automatically analyzed and updated in the background as changes are made by your editorial team.

To learn more, check out AWS Dominant Language.

Sentiment Detection

Add the f:aws-sentiment feature to a content type (or a single content instance) to have Amazon Comprehend's Sentiment Detection services automatically analyze your content's JSON and binary attachments to determine the overall sentiment being expressed.

The sentiment is stored back onto your content item along with a scoring breakdown and a final assessment ("positive", "negative", "neutral" and "mixed").

With this feature in place, your content will be automatically analyzed and updated in the background as changes are made by your editorial team.

To learn more, check out AWS Sentiment.