What does this AWS Solution do?
Analyzing Text with Amazon Comprehend and Amazon Elasticsearch Service is an automated reference implementation that deploys a cost-effective, end-to-end solution for extracting meaningful insights from unstructured data such as customer calls, support tickets, and online customer feedback. The solution leverages Amazon Comprehend, a natural language processing (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 visualization of extracted entities, key phrases, syntax, and sentiment from uploaded documentation.
AWS Solution overview
AWS offers a solution that uses AWS services for data ingestion and text analysis. The diagram below presents the architecture you can automatically deploy using the solution’s implementation guide and accompanying AWS CloudFormation template.
Analyzing Text with Amazon Elasticsearch Service and Amazon Comprehend architecture
The AWS CloudFormation template deploys an Amazon API Gateway to invoke the proxy microservice (AWS Lambda function). The microservice provides the business logic to manage preprocessing configuration, native indexing, and other native search capabilities. The microservice interacts with Amazon Comprehend for text analysis, Amazon CloudWatch Logs for logging and metrics, and Amazon Elasticsearch Service (Amazon ES) for indexing documentation.
An API receives an authorized request, the proxy microservice sends the request to Amazon Comprehend for text analysis. A call is made to Amazon ES which indexes the data, and publishes logs and metrics to CloudWatch.
You can visualize the indexed data on the solution’s pre-configured Kibana dashboard.