Overview - Analyzing Text with Amazon Elasticsearch Service and Amazon Comprehend

Overview

Many companies have large volumes of unstructured data such as customer calls, support tickets, and online customer feedback. But setting up a data pipeline and a natural language processing (NLP) engine to extract meaningful insights from this data can be a costly, labor-intensive process.

To help customers more easily set up a data pipeline and NLP engine, AWS offers Analyzing Text with Amazon Elasticsearch Service and Amazon Comprehend. This automated reference implementation deploys a cost-effective, end-to-end solution for data ingestion and text analysis. The solution leverages Amazon Comprehend, an NLP service that uses machine learning for text analysis, and Amazon Elasticsearch Service (Amazon ES) for indexing and analyzing unstructured text.

The solution also creates a pre-configured Kibana dashboard for the visualization of extracted entities, key phrases, syntax, and sentiment from uploaded documentation.

Cost

You are responsible for the cost of the AWS services used while running this solution. As of the date of publication, the cost for running this solution in the US East (N. Virginia) Region is approximately $0.775 per hour. This cost estimate includes the cost for running five Amazon ES on-demand m4.large.elasticsearch instances.

Note that the total cost for running this solution depends on the amount of time of running the Amazon ES cluster, and the amount of data being processed, stored, and presented. For full details, see the pricing webpage for each AWS service you will be using in this solution.