Amazon Comprehend is used to find meaningful insight by parsing text-based data. But some things you want to keep indecipherable, and this service can now help you keep personally identifiable information (PII) information hidden from text documents.
Amazon Comprehend uses natural language processing (NLP) in order to detect sensitive information like social security numbers, credit card numbers, and more. What is NLP? Natural language processing is a way for machines to analyze, understand, and derive meaning from text documents. You can glean important information from within the text itself, or meta-data about the data.
The AWS service also provides you the ability to derive the language of the text, key phrases, location, and even contextual sentiment from data sources like text on a web page, social media feeds, emails, or online articles. It’s a really powerful tool that illustrates some of the profound benefits and potential of artificial intelligence.
Not to mentioned the benefits of using a service that helps prevent your data from being compromised.
There’s nothing worse than your private information being leaked, hacked, or even taken and sold on the dark net. I’ve had previous email addresses and passwords hacked, and even this site at one point hacked because of how negligent I was when I set it up (I never figured I would turn this EC2 WordPress AMI into a daily blog about technology news and updates until two weeks after I had my instance up and running – and not once thought about securing the site until after the fact). It’s a terrifying feeling responding to an incident that was completely preventable. That’s why services like Amazon Comprehend play such an impactful role. Even when you may have private information in your text documents, Amazon Comprehend aids in making sure it doesn’t get out into the wrong hands (or machines).
Resources mentioned in this article:
