AWS Certified Machine Learning – Specialty — Question 281

A company hosts a public web application on AWS. The application provides a user feedback feature that consists of free-text fields where users can submit text to provide feedback. The company receives a large amount of free-text user feedback from the online web application. The product managers at the company classify the feedback into a set of fixed categories including user interface issues, performance issues, new feature request, and chat issues for further actions by the company's engineering teams.

A machine learning (ML) engineer at the company must automate the classification of new user feedback into these fixed categories by using Amazon SageMaker. A large set of accurate data is available from the historical user feedback that the product managers previously classified.

Which solution should the ML engineer apply to perform multi-class text classification of the user feedback?

Answer options

• A. Use the SageMaker Latent Dirichlet Allocation (LDA) algorithm.
• B. Use the SageMaker BlazingText algorithm.
• C. Use the SageMaker Neural Topic Model (NTM) algorithm.
• D. Use the SageMaker CatBoost algorithm.

Correct answer: B

Explanation

Amazon SageMaker BlazingText is highly optimized for supervised text classification, making it the ideal choice for classifying user feedback into predefined categories. In contrast, LDA and NTM are unsupervised topic modeling algorithms that group documents without predefined labels. While CatBoost can handle tabular data, BlazingText is specifically designed and optimized for natural language processing and text classification tasks.