Describe features of Natural Language Processing workloads on Azure →mediumMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
A market research company wants to analyze thousands of product reviews to identify the most frequently talked-about topics (such as 'battery life', 'screen quality', 'customer support') to guide product improvements. Which Azure AI Language feature is best suited for this task?
⚠ Common exam trap
Test-takers frequently confuse key phrase extraction with entity recognition, assuming that any 'named' item (like a product feature) is an entity, but entity recognition is strictly for predefined categories like Person, Location, Organization, not for abstract or product-specific topics.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Key phrase extraction
Key phrase extraction is designed to identify the main points or topics in a body of text, making it the ideal choice for surfacing frequently mentioned themes like 'battery life' or 'screen quality' from thousands of product reviews. It returns a list of key phrases that represent the most salient concepts, directly supporting the goal of guiding product improvements based on customer feedback.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Sentiment analysis
Why it's wrong here
Sentiment analysis assigns a polarity score (positive, negative, neutral, or mixed) to the entire text or individual sentences by detecting subjective language and emotional tone. While it can tell you that customers feel negatively about a product, it does not isolate the specific aspects or topics driving that sentiment, such as 'battery life' or 'ease of use'.
- ✓
Key phrase extraction
Why this is correct
Key phrase extraction uses natural language processing to scan the text and pull out the most salient words and phrases that represent the main subjects discussed. In product reviews, this surfaces concrete topics like 'battery life', 'screen quality', or 'customer support', making it the correct choice for identifying what customers are talking about across thousands of documents.
- ✗
Entity recognition
Why it's wrong here
Entity recognition, also called named entity recognition (NER), identifies and classifies specific, predefined categories of named entities such as people, organizations, locations, dates, and products (e.g., 'Microsoft', 'Paris', 'Q3'). It does not extract general, abstract topics or key phrases like 'screen quality' or 'battery life', which are not tied to a named entity type in a knowledge base.
- ✗
Language detection
Why it's wrong here
Language detection identifies the natural language in which the text is written, such as English, French, or German, by analyzing character patterns and linguistic features. It gives no information about the content, topics, or themes discussed within the text, so it cannot reveal what aspects of a product customers are mentioning.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
Key term
Azure AI Language
Azure AI Language is a cloud-based service from Microsoft that uses natural language processing to understand, analyze, and generate human language for applications.
Key term
Feature
A feature is a distinct unit of functionality that delivers value to the user, often managed and tracked throughout the software development lifecycle.
About these practice questions
One of 985 original AI-900 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.