AWS Certified Solutions Architect – Associate (SAA-C03) — Question 771

A marketing team wants to build a campaign for an upcoming multi-sport event. The team has news reports from the past five years in PDF format. The team needs a solution to extract insights about the content and the sentiment of the news reports. The solution must use Amazon Textract to process the news reports.

Which solution will meet these requirements with the LEAST operational overhead?

Answer options

• A. Provide the extracted insights to Amazon Athena for analysis. Store the extracted insights and analysis in an Amazon S3 bucket.
• B. Store the extracted insights in an Amazon DynamoDB table. Use Amazon SageMaker to build a sentiment model.
• C. Provide the extracted insights to Amazon Comprehend for analysis. Save the analysis to an Amazon S3 bucket.
• D. Store the extracted insights in an Amazon S3 bucket. Use Amazon QuickSight to visualize and analyze the data.

Correct answer: C

Explanation

Amazon Textract is used to extract raw text from PDF documents, but it cannot analyze sentiment or extract deeper NLP insights. Amazon Comprehend is a fully managed service that performs sentiment analysis and keyphrase extraction on text with minimal operational overhead, making it the ideal next step before saving the results to Amazon S3. Other options like Amazon SageMaker require high operational overhead to build custom models, while Amazon Athena and Amazon QuickSight lack built-in sentiment analysis capabilities for raw text.