Exam AWS Certified Machine Learning - Specialty topic 1 question 281 discussion

This approach uses Amazon Comprehend's asynchronous batch processing. By uploading the data to S3 and using the StartSentimentDetectionJob API, Comprehend can process the entire dataset in parallel. This is the most efficient method for large datasets.

This approach uses Amazon Comprehend's asynchronous batch processing. By uploading the data to S3 and using the StartSentimentDetectionJob API, Comprehend can process the entire dataset in parallel. This is the most efficient method for large datasets.

C is a async method, A, B is not. https://docs.aws.amazon.com/comprehend/latest/APIReference/API_StartSentimentDetectionJob.html

C is the most efficient approach

This method is the most efficient and scalable for processing a dataset of this size, significantly outperforming the other options in terms of processing time.

since there are million post, 15 minutes may not be enough so step function is needed and batchDetectSentiment is good way to go

https://docs.aws.amazon.com/comprehend/latest/APIReference/API_BatchDetectSentiment.html#API_BatchDetectSentiment_RequestParameters

It's B. Limit on BatchDetectSentiment is 25 documents. Other endpoints are for individual strings.

B. Use a combination of AWS Step Functions and an AWS Lambda function to call the BatchDetectSentiment API operation with batches of up to 25 posts at a time. Batch processing is generally more efficient for large datasets. The BatchDetectSentiment API operation allows you to process multiple items (up to 25) in a single call, which helps in reducing the overall processing time. Additionally, using AWS Step Functions to manage the workflow and AWS Lambda to handle the batch processing can make the implementation scalable and easier to manage.