Amazon Comprehend is Amazon’s service for natural language processing and Text analysis. Examples include Customer emails, support tickets, product reviews, social media, even advertising copy represents insights into customer sentiment that can be put to work for your business.
The Amazon Comprehend activities give you the ability to automate interactions with the Amazon Comprehend service. Using the Amazon Comprehend APIs, this activities package provides you with the following text and document analysis capabilities:
Phrase Extraction: returns the key phrases or talking points and a confidence score to support that this is a key phrase.
Sentiment Analysis: overall sentiment of a text (Positive, Negative, Neutral, or Mixed).
Syntax Analysis: tagging verbs, etc.
Entity Recognition: returns the named entities (“People,” “Places,” “Locations,” etc.) that are automatically categorized based on the provided text.
Multiple Language Support
Medical Ontology Linkage
How it works
To enable the outbound automation between UiPath and Amazon Comprehend, the Amazon Comprehend activities establish an authenticated connection to your AWS resources via the Amazon Scope activity.
After your connection is established, you can add the other Amazon Comprehend activities to create new automation projects, or add them to existing projects.
How does it connect?
This is where we need your help.
To establish an authenticated connection, the Amazon Textract activities need authorization from the AWS Identity and Access Management (IAM) service.
To enable AWS IAM authorization, you create or use an existing IAM user and generate access keys (Access Key Id and Secret Access Key). When creating your IAM user, you assign the policies and permissions that specify the resources your Robot can access (e.g., AmazonTextractFullAccess).
After creating your IAM user and assigning your policies, you enter the Access Key Id and Secret Access Key in the Amazon Scope activity. When you run your automation project, the keys are used to sign the API requests being made by each of the activities.
Each Amazon Comprehend activity calls a Amazon Comprehend API using the request parameters you enter in the activity’s input properties. If the call is successful, the activity outputs the relevant response elements (i.e., output properties) that you can use as input property values in subsequent activities, queue items in an existing Queue, and etc.
For a complete list of the Amazon Comprehend APIs used by each activity and links to the relevant API documentation, see the Technical References page. You don’t need to be familiar with the Amazon Comprehend APIs to use the activities. These links are for informational purposes only in case you want to learn more about the action happening “behind-the-scenes”.
Before you build your first project, complete the steps in the Setup guide. To learn more about the Amazon Textact activities (including example property inputs/outputs), see the Activities page for a complete activity list and links to the activity detail pages.