A data scientist is using Amazon Comprehend to perform sentiment analysis on a dataset of one million social media posts. Which approach will process the dataset in the LEAST time?

Question

Options

• AUse a combination of AWS Step Functions and an AWS Lambda function to call the
• BUse a combination of AWS Step Functions and an AWS Lambda function to call the
• CUpload the posts to Amazon S3. Pass the S3 storage path to an AWS Lambda function that calls
• DUse an AWS Lambda function to call the BatchDetectSentiment API operation with the whole

• A
  4% (1)
• B
  67% (16)
• C
  17% (4)
• D
  13% (3)

Explanation

For large-scale batch sentiment analysis, Amazon Comprehend's asynchronous batch processing job (StartSentimentDetectionJob) is the fastest approach. It is designed for high-throughput processing of large document sets stored in S3 and runs the workload in parallel on managed infrastructure. Option B uses Step Functions with a Lambda function to invoke the Comprehend asynchronous batch job API, which handles millions of documents efficiently. Option D (BatchDetectSentiment) processes only up to 25 documents per API call synchronously, making it impractical for one million posts without massive parallelism overhead. Options A and C involve synchronous calls that would be rate-limited and slow at this scale. The asynchronous job approach in option B is purpose-built for this volume.

No community discussion yet for this question.