Describe features of Natural Language Processing workloads on Azure →easyMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
A customer service team wants to automatically determine whether each customer feedback message is positive, negative, or neutral. Which Azure AI Language feature should they use?
⚠ Common exam trap
It's easy for candidates to confuse sentiment analysis with key phrase extraction or entity recognition, thinking that extracting important words or entities can imply sentiment, but only sentiment analysis directly provides the positive/negative/neutral classification.
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
✓
Sentiment analysis
Sentiment analysis is the correct Azure AI Language feature because it is specifically designed to classify text into positive, negative, or neutral sentiments. This directly matches the customer service team's requirement to automatically determine the sentiment of each feedback message. Other features like key phrase extraction or entity recognition do not perform sentiment classification.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Key phrase extraction
Why it's wrong here
Key phrase extraction, part of Azure AI Language, scans the text and returns a list of significant words and short phrases like "software bug" or "great customer support." It produces no polarity or confidence score, so a phrase such as "terrible delay" is extracted as an important term but never labeled as expressing a negative opinion. This makes it useful for summarizing topics, not for determining customer sentiment.
- ✗
Language detection
Why it's wrong here
Language detection examines the script, character frequency, and linguistic patterns to identify the dominant language (for example, English or Spanish) and returns a language code like "en" or "es" along with a confidence score. It simply classifies the medium of the text, not the author's attitude. The team could tell that a review is in French, but the service gives them zero information about whether the review is favorable or unfavorable.
- ✓
Sentiment analysis
Why this is correct
Sentiment analysis, another Azure AI Language capability, evaluates raw text and returns aggregate sentiment scores—positive, neutral, and negative—for both the entire document and each individual sentence. The scores sum to 1.0, and the model is trained on review-like data, which can be used to infer an emotional tendency in the customer's words. Because the requirement is specifically to determine whether feedback is positive, negative, or neutral, sentiment analysis directly fulfills that purpose.
- ✗
Entity recognition
Why it's wrong here
Entity recognition (NER) identifies and classifies named entities such as people, organizations, locations, dates, and products, assigning each mention a category and a confidence score. It would tell you that "Acme Corp" is an organization or "Airline X" is a product, but it does not assign any sentiment or opinion polarity to those entities. This means it can find what is being discussed, but not the customer's disposition toward it.
Go deeper
Related to this question
Learn chapter
Regression and Classification
Key term
Classification
Classification is a supervised machine learning technique used to predict a category or class label for new data based on patterns learned from labeled training data.
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
This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam 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.