Posted On: Sep 21, 2022

Amazon Comprehend customers can now extract the sentiments associated with entities from text documents in real-time using the newly released synchronous API. Targeted Sentiment synchronous API enables customers to derive granular sentiments associated with specific entities of interest such as brands or products without waiting for batch processing.

Amazon Comprehend is a natural language processing (NLP) service that provides APIs to extract key phrases, contextual entities, events, and sentiment from text. Amazon Comprehend provided sentiment APIs to analyze overall sentiment for a text document, as well as targeted sentiment APIs to analyze sentiments associated with entities within a text document. Until today, customers could run asynchronous jobs for targeted sentiment. Now, customers will be able to perform real-time analysis to identify sentiments associated with entities in their text documents. Given a text document such as a customer review or a call transcription, Targeted Sentiment extracts the entities mentioned in the text such as ‘burger’, ‘service’, or ‘price’, and identifies the sentiment expressed about those entities. Also, targeted sentiment identifies sentiments associated with a group of entity mentions that belong to the same entity group. For example, customers can extract the sentiment for an entity “burger”, even if it is referred to as "the burger", "Hamburger Deluxe", and "it" within the text.

To learn more and get started, visit the Amazon Comprehend launch blog post, product page and our documentation.