Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to find insights and relationships in text. Amazon Comprehend identifies the language of the text; extracts key phrases, places, people, brands, or events; understands how positive or negative the text is; and automatically organizes a collection of text files by topic.
There is a very low learning curve to get started with the service, processing data is easy and the results are quite accurate from what we have seen thus far.
What do you dislike?
The management interface lacks some functionality, although it is a fairly new product, so I expect that to change over time. As of now, you cannot manually delete jobs you no longer need.
Recommendations to others considering the product
It takes almost no time to do a proof of concept as long as you have data available to process.
What business problems are you solving with the product? What benefits have you realized?
Analyzing user feedback submissions to compare their number ratings with the sentiment detected from the text. It has helped more accurately classify and group the feedback. This allows us to more easily and accurately prioritize system improvements.
* We monitor all Amazon Comprehend reviews to prevent fraudulent reviews and keep review quality high. We do not post reviews by company employees or direct competitors. Validated reviews require the user to submit a screenshot of the product containing their user ID, in order to verify a user is an actual user of the product.