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 marketing team needs to analyze thousands of product reviews to identify the most frequently mentioned topics, such as 'battery life', 'customer support', and 'price'. They want an automated method to extract these main concepts from each review. Which Azure AI Language feature should they use?
⚠ Common exam trap
A common mix-up: candidates confuse key phrase extraction with entity recognition, as both extract information from text, but entity recognition is limited to predefined categories (e.g., person, location) while key phrase extraction captures any salient concept.
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 the correct choice because it automatically identifies the main concepts, such as 'battery life', 'customer support', and 'price', from unstructured text like product reviews. This feature is specifically designed to extract the most salient topics or points from a document, making it ideal for analyzing thousands of reviews to find frequently mentioned themes.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Language detection
Why it's wrong here
Language detection is a text analytics capability that uses machine learning to identify the written language of a document, returning a language code and confidence score. It classifies linguistic identity (e.g., English, Spanish, French) but does not analyze the semantic content or subject matter. For product reviews, language detection only tells you what language the review is written in, not what aspects of the product customers are discussing, so it cannot reveal topics like 'battery life' or 'durability.'
- ✗
Sentiment analysis
Why it's wrong here
Sentiment analysis evaluates the emotional tone of text, assigning polarity scores (positive, negative, neutral, or mixed) at both document and sentence levels. It measures the attitude expressed but does not extract the specific subjects or concepts behind that sentiment. For example, a review stating 'battery drains fast but the camera is amazing' yields mixed sentiment, yet sentiment analysis will not surface that 'battery life' and 'camera quality' are the discussed topics—it only quantifies the overall feeling.
- ✓
Key phrase extraction
Why this is correct
Key phrase extraction is an Azure AI Language feature that uses natural language processing to identify the most salient words and phrases in a document, typically noun phrases and adjective-noun combinations that represent the main concepts or topics. It returns phrases such as 'battery life,' 'customer support,' or 'ease of setup,' which directly correspond to the subjects customers mention in product reviews. This makes it the correct choice for analyzing thousands of reviews to uncover recurring themes and product aspects.
- ✗
Entity recognition
Why it's wrong here
Named Entity Recognition (NER) extracts specific pre-defined categories such as persons, organizations, locations, dates, quantities, and URLs, along with confidence scores. It is designed to identify discrete, well-defined entities rather than broad topic phrases like 'battery life' or 'build quality.' Without custom entity definitions for every product attribute, NER would miss most of the conceptual topics that appear across varied product reviews, making it unsuitable for open-ended topic analysis.
Go deeper
Related to this question
Learn chapter
Machine Learning Core Concepts
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.
Key term
Key phrase extraction
Key phrase extraction is an Azure AI service feature that automatically identifies and extracts the most important words and phrases from a piece of text.
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.