PubNub Integration

Amazon Comprehend - Discover text insights and relationships



Last Updated:





Use natural language processing (NLP) to find insights and relationships in text. No machine learning experience required.

Amazon Comprehend provides Keyphrase Extraction, Sentiment Analysis, Entity Recognition, Topic Modeling, and Language Detection APIs so you can easily integrate natural language processing into your applications. You simply call the Amazon Comprehend APIs in your application and provide the location of the source document or text. The APIs will output entities, key phrases, sentiment, and language in a JSON format, which you can use in your application. With Amazon Comprehend, you only pay for what you use. You are charged based on the amount of text processed.

Amazon Comprehend - Discover text insights and relationships


Begin by adding the AWS keys to the vault storage by using the MY SECRETS feature from within the blocks editor. The block will need the AWS_access_key and AWS_secret_key values.

This PubNub Functions listens for all chats  and allows to add comprehension even in private chats.

To trigger comprehension determination, event payload should contain 'comprehend' field in it with following keys:   - location - name of key in event payload, which contain data for comprehension   - language - code of language on which passed message has been written


    "data": {
        "text": "hello!",
        "comprehend": {
            "language": "en",
            "location": "text"


    "Sentiment": "NEUTRAL",
    "SentimentScore": {
        "Mixed": 0.009615407325327396,
        "Negative": 0.062095608562231064,
        "Neutral": 0.7428858280181885,
        "Positive": 0.18540318310260773

Feedback & Support

Need help? Contact PubNub Support.

Talk to an expert

Contact Sales