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 retail company collects thousands of customer reviews. They want to automatically extract frequently mentioned aspects (e.g., 'battery life', 'customer service', 'price') to understand common topics. Which Azure AI Language capability should they use?
⚠ Common exam trap
Watch out — candidates often confuse 'key phrase extraction' with 'named entity recognition' because both deal with extracting information from text, but NER is limited to predefined entity types (e.g., person, location) while key phrase extraction handles arbitrary descriptive phrases.
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 Azure AI Language capability because it is specifically designed to identify and extract the main talking points or topics from unstructured text, such as 'battery life', 'customer service', and 'price' from customer reviews. This directly matches the requirement to automatically extract frequently mentioned aspects without needing predefined categories.
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, or neutral) to the entire text or individual sentences, but it does not isolate which specific aspects (e.g., 'battery life', 'screen quality') are being praised or criticized. The output is an aggregate emotion score, not a list of topics or product features, so it cannot reveal which aspects are frequently mentioned across thousands of reviews.
When this WOULD be correct
A company wants to automatically classify customer reviews as positive, negative, or neutral to gauge overall satisfaction. Sentiment analysis would be the correct Azure AI Language capability for this task.
- ✓
Key phrase extraction
Why this is correct
Key phrase extraction returns the main topics, themes, and descriptive phrases from text by analyzing linguistic features like term frequency and co-occurrence. In the Azure AI Language service, this API scans unstructured text and surfaces salient phrases such as 'long battery life' or 'camera clarity', making it the ideal choice for discovering what customers repeatedly mention about products.
- ✗
Named entity recognition
Why it's wrong here
Named entity recognition identifies references to predefined entities such as persons, organizations, locations, dates, and quantities—for example, 'Microsoft' or 'Seattle'—but it does not extract general descriptive phrases like 'battery life' or 'price point'. It is designed for structured entity types, not open-ended product features, so it would miss the very aspects the company wants to analyze.
When this WOULD be correct
A question asks: 'Which Azure AI Language capability should be used to extract specific entities such as product names, company names, or locations from customer feedback?'
- ✗
Language detection
Why it's wrong here
Language detection identifies the written language of a text (e.g., English, Spanish, French) by returning a language code and confidence score, but it does not interpret the content's subject matter. Because the goal is to find recurring product aspects, not the language used in reviews, this capability would be irrelevant to the analysis.
When this WOULD be correct
A multinational company receives customer feedback in multiple languages and needs to automatically route each review to the appropriate language-specific processing pipeline. Language detection would be the correct choice to identify the language of each review.
Option-by-option analysis
Why each answer is right or wrong
Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.
✓Key phrase extractionCorrect answer▾
Why this is correct
Key phrase extraction returns the main topics, themes, and descriptive phrases from text by analyzing linguistic features like term frequency and co-occurrence. In the Azure AI Language service, this API scans unstructured text and surfaces salient phrases such as 'long battery life' or 'camera clarity', making it the ideal choice for discovering what customers repeatedly mention about products.
✗Sentiment analysisWrong answer — click to see why▾
Why this is wrong here
Sentiment analysis determines the emotional tone (positive, negative, neutral) of text, not the extraction of frequently mentioned aspects or topics. The question asks for identifying common topics like 'battery life', which requires key phrase extraction.
★ When this WOULD be the correct answer
A company wants to automatically classify customer reviews as positive, negative, or neutral to gauge overall satisfaction. Sentiment analysis would be the correct Azure AI Language capability for this task.
Why candidates choose this
Candidates may confuse sentiment analysis with aspect-based analysis, assuming that understanding topics involves detecting sentiment, but sentiment analysis does not extract specific aspects.
✗Named entity recognitionWrong answer — click to see why▾
Why this is wrong here
Named entity recognition identifies specific entities like people, organizations, or locations, not general aspects or topics like 'battery life' or 'customer service' that are frequently mentioned across reviews.
★ When this WOULD be the correct answer
A question asks: 'Which Azure AI Language capability should be used to extract specific entities such as product names, company names, or locations from customer feedback?'
Why candidates choose this
Candidates may confuse 'entities' with 'aspects' or topics, assuming that extracting named entities would also capture common topics mentioned in reviews.
✗Language detectionWrong answer — click to see why▾
Why this is wrong here
Language detection identifies the language of text, not the extraction of frequently mentioned aspects like 'battery life' or 'price'. The question requires extracting specific topics, not detecting the language.
★ When this WOULD be the correct answer
A multinational company receives customer feedback in multiple languages and needs to automatically route each review to the appropriate language-specific processing pipeline. Language detection would be the correct choice to identify the language of each review.
Why candidates choose this
Candidates may confuse language detection with text analysis capabilities, thinking that detecting the language is a prerequisite for understanding topics, but the question specifically asks for extracting mentioned aspects, not language identification.
Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Service
A service is a software component or system that performs a specific function and is available to be used by other programs or users over a network.
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.
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. 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.