You work as a machine learning specialist for an online retail company that sells health products. Your company allows users to enter reviews of the products they buy from the website. You want to make sure the reviews do not contain any offensive or unsafe content, such as obscenities or threatening language.
Which Amazon SageMaker algorithm or Amazon service will allow you to scan your user’s review text in the simplest way?

Answer options:

A.BlazingText
B.Neural Topic Model (NTM)
C.Semantic Segmentation
D.Comprehend

Answer: D
Option A is incorrect. The BlazingText algorithm is used for natural language processing tasks like sentiment analysis, and named entity recognition. You should use all of these features when scanning your user’s review text. However, the BlazingText algorithm requires more developer effort and time than using the Comprehend service.
Option B is incorrect. The Neural Topic Model algorithm is used to group documents into topics using the statistical distribution of words within the documents. This algorithm would not be the most efficient choice for detecting offensive or unsafe language.
Option C is incorrect. The Semantic Segmentation algorithm is used for computer vision applications. So it is not an algorithm you would use for text analysis.
Option D is correct. The Comprehend service scans your unstructured review text and analyzes it using SageMaker Natural Language Processing (NLP) algorithms to find key phrases, entities, and sentiments. This is the most expeditious and efficient option.
Reference:
Please see the Amazon SageMaker developer guide titled Using Amazon SageMaker Built-in Algorithms, and the Amazon Machine Learning blog titled Analyze content with Amazon Comprehend and Amazon SageMaker notebooks.
Here is a diagram of the solution: