Process customer reviews to find positive or negative sentiment and named entities.
Do not train a custom model.
Which service is most appropriate?
Amazon Comprehend extracts sentiment, entities, and key phrases from text with managed NLP capabilities.
Detailed explanation
Athena queries data with SQL but is not an NLP model service.
Athena queries data with SQL but is not an NLP model service.
Transcribe converts audio to text; it does not perform the requested text sentiment analysis.
Transcribe converts audio to text; it does not perform the requested text sentiment analysis.
Comprehend analyzes text for sentiment, entities, key phrases, and related NLP features.
Comprehend analyzes text for sentiment, entities, key phrases, and related NLP features.
Rekognition analyzes images and video rather than primarily analyzing text sentiment.
Rekognition analyzes images and video rather than primarily analyzing text sentiment.
Check official documentation
Compare the following points with the official documentation.
Amazon Comprehendの公式概要で、感情分析とエンティティ認識を確認する。
Official references
What to confirm
レビューの自然言語分析にComprehendを選べる。
Key points
- Amazon Comprehend
- Sentiment analysis
- Entities
Notes
- Environment:
- AI/ML and analytics service features can change; confirm current behavior in official AWS documentation.
Foundation review
Input and output direction
Separate image analysis, speech-to-text, and text-to-speech by the direction and type of transformation.
Pipeline stage
A query, model inference, dashboard, and data-ingestion service solve different stages of an analytics workflow.