Amazon Comprehend

Discover insights and relationships in text

Amazon Comprehend is a machine learning powered service that makes it easy to find insights and relationships in text.

Customer emails, support tickets, product reviews, call center conversations, and social media contain a rich amount of information about your business. However, because this type of data is unstructured and messy, it’s hard to extract relevant and meaningful insights at scale. As a result, most of it goes unused. Amazon Comprehend solves this problem using natural language processing (NLP) to automatically identify the language of the text, extract key phrases, places, people, brands, or events; understand positive or negative sentiment; and automatically organize a collection of text files by topic. To build a custom set of entities or text classification models that are tailored uniquely to your organization’s needs you can use AutoML, or to extract complex medical information from unstructured text, you can use Amazon Comprehend Medical.


Get insights from your text

Organize documents by topics

Fully customizable

Deep support for healthcare

Discover the meaning and relationships in text from customer support incidents, product reviews, social media feeds, news articles, documents, and other sources. For example, you can identify the feature that’s mentioned most often when customers are happy or unhappy about your product.

Automatically organize text files by relevant terms or topics. For example, if you have an extensive collection of news articles, you can automatically group them by subject matter for use in a recommendation engine that suggests new articles to read based on past behavior.

Identify specific terms, such as policy numbers or part codes, and classify documents and messages in a way that makes sense for your business. Simply provide your labels and a small set of examples for each, and Comprehend takes care of the rest.

Amazon Comprehend Medical provides additional capabilities to identify medical information such as medical conditions, medications, dosages, strengths, and frequencies from a variety of sources like doctor’s notes, clinical trial reports, and patient health records.

How it works


Use cases

Voice of customer analytics

Analyze customer interactions from support emails, social media posts, online comments, telephone transcriptions, etc., and discover what factors drive the most positive and negative experiences. You can then use these insights to improve your products and services.

Create a better search experience by enabling your site’s search engine to index key phrases, entities, and sentiment. This focuses the search on the query’s intent and the context of the articles instead of basic keywords.

Knowledge management and discovery

You can use Amazon Comprehend to organize and categorize your documents by topic for easier discovery, and then personalize content recommendations for readers by recommending other articles related to the same topic.

Classify and route support tickets

Categorize inbound customer support documents automatically based on their content, e.g. account cancellation requests, billing problems, or change of address. You can also automatically extract relevant information like part numbers, loyalty tiers, and product names to quickly route documents the team best equipped to solve the problem.

Perform Medical Cohort Analysis

In oncology, it is critical that the right selection criteria are quickly discovered and used to recruit patients for clinical trials. Amazon Comprehend Medical understands and identifies complex medical information found in unstructured text to help make indexing and searching easier. You can use these insights to identify recruit patients to the appropriate clinical trial in a fraction of the time and cost from manual selection processes.

Get started with AWS

Step 1 - Sign up for an AWS account

Sign up for an AWS account

Instantly get access to the AWS Free Tier.

Learn with 10-minute Tutorials

Explore and learn with simple tutorials.

Start building with AWS

Begin building with step-by-step guides to help you launch your AWS project.

Learn more about Amazon Comprehend

Visit the features page
Ready to build?
Have more questions?
Contact us