Sign in
Sign in
or
Create a new account
Categories
Your Saved List Partners Sell in AWS Marketplace Amazon Web Services Home Help
Amazon SageMaker ×

Amazon SageMaker is a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. With Amazon SageMaker, all the barriers and complexity that typically slow down developers who want to use machine learning are removed. The service includes models that can be used together or independently to build, train, and deploy your machine learning models.

Opinion Mining - Sentiment Analysis

By: ElectrifAi LLC Latest Version: 1.0.0

Breakdown and analyze sentiment of every aspect present within a text document

Product Overview

This algorithm takes sentiment analysis a step further by extracting each aspect and opinion within any text document. As opposed to producing sentiment scores on the entirety of a sentence, paragraph, or document, this algorithm identifies the entity being discussed, the aspect of that entity, and the opinion being discussed about that aspect. This granular approach provides a more in-depth view into customer sentiment that other models overlook. Our machine learning models are available through a Private Offer. Please contact info@electrifai.net for subscription service pricing. SKU: OPMSA-PS-TAT-AWS-001

Key Data

Version
By ElectrifAi LLC
Categories
Type Model Package
Fulfillment Methods Amazon SageMaker

Usage Information

Fulfillment Methods

Amazon SageMaker

Usage Instructions

Input

Supported content types: application/json Sample input:
{ "content": "The park was very fun. It was an excellent vacation." }

Output

Content type: application/json Sample output:
{ "result": [ { "sentence": "The park was very fun.", "aspect": "park", "opinion": "fun", "sentiment": 7.9530860965 }, { "sentence": "It was an excellent vacation.", "aspect": "vacation", "opinion": " excellent", "sentiment": 8.008627331 } ] }

Invoking endpoint

AWS CLI Command aws sagemaker-runtime invoke-endpoint --endpoint-name $endpoint_name --body '$json_input' --content-type 'application/json' --region us-east-2 output.json

Replace the following parameters:

  • endpoint_name – inference endpoint name
  • json_content – json input
  • output.json – output file

Resources

Sample Notebook : https://github.com/ElectrifAi/model-aws-opinion-mining-sentiment-analysis/raw/master/OpinionMiningSentimentAnalysis_Model_Package.ipynb

Additional Resources

End User License Agreement

By subscribing to this product you agree to terms and conditions outlined in the product End User License Agreement (EULA)

Support Information

AWS Infrastructure

AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services. Learn more

Refund Policy

According to contract

Customer Reviews