Courseiva

AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure

A hospital collects patient feedback forms in text format. They want to automatically identify whether each feedback is positive, negative, or neutral, and also extract specific recurring phrases like 'waiting time' and 'staff attitude'. Which Azure AI Language feature should they use to determine the overall tone of the feedback?

⚠ Common exam trap

Candidates often confuse key phrase extraction (which extracts phrases like 'waiting time') with sentiment analysis, but key phrase extraction does not determine tone—it only identifies significant terms without any sentiment scoring.

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

C) Sentiment analysis

Sentiment analysis is the correct Azure AI Language feature because it is specifically designed to determine the overall tone (positive, negative, or neutral) of text. The question asks for identifying the tone of feedback, which is exactly what sentiment analysis provides by scoring each document and its sentences for sentiment polarity.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • A) Key phrase extraction

    Why it's wrong here

    Key phrase extraction in Azure AI Language identifies salient words and multi-word expressions (e.g., 'long wait time', 'nurse professionalism') that define the main topics in a patient's feedback. It does not, however, assign an emotional label or polarity to the text, so it cannot reveal whether the opinion is positive or negative. This makes it a poor fit for the stated task of determining the overall tone of the feedback.

  • B) Entity recognition

    Why it's wrong here

    Entity recognition (NER) uses a pretrained model to locate and categorize named entities such as persons, organizations, locations, dates, and medical terms into predefined types. For a patient comment, it might detect 'Emergency Department' as a location or 'Dr. Smith' as a person, but it produces no judgment about the expressed sentiment. Since the hospital needs to gauge satisfaction — not just extract factual references — NER fails to address the core requirement.

  • C) Sentiment analysis

    Why this is correct

    Sentiment analysis is a text classification capability in Azure AI Language that evaluates each input document or sentence and returns a sentiment label (positive, negative, neutral, or mixed) along with confidence scores. Under the hood, it uses trained machine learning models on contextual embeddings to capture how the overall attitude is expressed. This directly matches the task of identifying the overall tone of patient feedback, making it the correct choice.

  • D) Language detection

    Why it's wrong here

    Language detection scans the text and, based on character n-grams and word patterns, identifies the dominant language in which it is written (e.g., English, Spanish, or French). It does not attempt to interpret meaning, opinion, or emotion; a negative complaint in English is treated identically to a positive one in the same language. Consequently, while it is useful for routing feedback to a translator, it cannot evaluate the tone of the content.

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 →

How Courseiva writes practice questions · Editorial policy

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.