Describe features of Natural Language Processing workloads on Azure →mediumMultiple ChoiceObjective-mapped
Prebuilt Key Phrase Extraction and Sentiment Analysis for Customer Support
A customer service team wants to analyze thousands of call transcripts to identify common complaints and understand whether customer sentiment is positive, negative, or neutral. They plan to use prebuilt Azure AI Language features without any custom training. Which combination of features should they use?
Quick Answer
The correct combination is key phrase extraction and sentiment analysis. This is because the customer service team needs to identify common complaints from thousands of call transcripts, which requires pulling out recurring topics and main talking points—exactly what prebuilt key phrase extraction does—while also determining whether customer sentiment is positive, negative, or neutral, which is the job of sentiment analysis. On the AI-900 exam, this scenario tests your understanding of Azure AI Language’s prebuilt, no-code features; a common trap is confusing key phrase extraction with named entity recognition, but remember that key phrases capture general themes, not specific people or places. The search intent for prebuilt key phrase extraction and sentiment analysis for customer support transcripts is fully met here because both features work out-of-the-box without custom training. Memory tip: think “Phrases for problems, Sentiment for feelings.”
⚠ Common exam trap
Candidates often confuse 'key phrase extraction' with 'entity recognition' or assume that 'conversation analysis' alone can extract complaints and sentiment, when in fact the correct combination requires two distinct prebuilt features that directly map to the two stated goals (identifying common complaints and understanding sentiment).
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 and sentiment analysis
The customer service team needs to identify common complaints (which requires extracting key phrases from the call transcripts) and understand sentiment polarity (positive, negative, or neutral). Azure AI Language's prebuilt key phrase extraction returns the main talking points and recurring terms, while sentiment analysis assigns a sentiment score and labels per sentence or document. Both features are available out-of-the-box without any custom training, directly meeting the stated requirements.
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 and sentiment analysis
Why this is correct
Key phrase extraction pulls out important talking points (complaints); sentiment analysis assigns a positive/negative/neutral score. Together they meet both needs.
- ✗
Entity recognition and text translation
Why it's wrong here
Entity recognition finds names/locations, not complaints; text translation changes language, which is not needed for understanding complaints or sentiment.
When this WOULD be correct
A multinational company needs to extract names of people, organizations, and locations from multilingual customer feedback and then translate the feedback into English for centralized analysis. In this scenario, entity recognition and text translation would be the correct combination.
- ✗
Language detection and summarization
Why it's wrong here
Language detection identifies the language of the text; summarization provides a short version but does not extract key phrases or sentiment.
When this WOULD be correct
A scenario where the team needs to identify the language of multilingual transcripts and then generate concise summaries of each call to quickly review key points, without needing sentiment or complaint extraction.
- ✗
PII detection and conversation analysis
Why it's wrong here
PII detection finds sensitive data like phone numbers; conversation analysis is for understanding dialogue structure, not extracting complaints or sentiment.
When this WOULD be correct
A healthcare organization needs to scan patient call transcripts to detect and redact personally identifiable information (PII) for compliance, while also analyzing conversation structure to evaluate agent performance. In that scenario, PII detection and conversation analysis would be the correct combination.
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 extraction and sentiment analysisCorrect answer▾
Why this is correct
Key phrase extraction pulls out important talking points (complaints); sentiment analysis assigns a positive/negative/neutral score. Together they meet both needs.
✗Entity recognition and text translationWrong answer — click to see why▾
Why this is wrong here
Entity recognition identifies named entities (e.g., people, places) but does not extract key phrases or assess sentiment; text translation changes language but does not analyze complaints or sentiment. The task requires identifying common complaints (key phrases) and sentiment, which entity recognition and translation do not provide.
★ When this WOULD be the correct answer
A multinational company needs to extract names of people, organizations, and locations from multilingual customer feedback and then translate the feedback into English for centralized analysis. In this scenario, entity recognition and text translation would be the correct combination.
Why candidates choose this
Candidates may think entity recognition helps identify complaint topics (e.g., product names) and translation is needed for multilingual transcripts, overlooking that key phrase extraction is specifically designed for identifying common themes and sentiment analysis for emotional tone.
✗Language detection and summarizationWrong answer — click to see why▾
Why this is wrong here
Language detection identifies the language of text, and summarization condenses content, but neither extracts specific complaints nor determines sentiment polarity, which are the core requirements.
★ When this WOULD be the correct answer
A scenario where the team needs to identify the language of multilingual transcripts and then generate concise summaries of each call to quickly review key points, without needing sentiment or complaint extraction.
Why candidates choose this
Candidates may think summarization can extract complaints and language detection is a common first step, overlooking that the question explicitly requires identifying complaints and sentiment, not just summarizing or detecting language.
✗PII detection and conversation analysisWrong answer — click to see why▾
Why this is wrong here
PII detection identifies personal data (e.g., names, SSNs) and conversation analysis extracts structured insights like call summaries or agent-customer dynamics, but neither directly identifies common complaints nor classifies sentiment as positive, negative, or neutral.
★ When this WOULD be the correct answer
A healthcare organization needs to scan patient call transcripts to detect and redact personally identifiable information (PII) for compliance, while also analyzing conversation structure to evaluate agent performance. In that scenario, PII detection and conversation analysis would be the correct combination.
Why candidates choose this
Candidates may confuse 'conversation analysis' with sentiment analysis, assuming it includes sentiment detection, or think that identifying personal data is a prerequisite for understanding complaints, leading them to select this option without reading the requirements carefully.
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
Sentiment analysis
Sentiment analysis is a natural language processing technique that uses machine learning to determine the emotional tone or opinion expressed in a piece of text.
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 →
Same concept, more angles
4 more ways this is tested on AI-900
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A customer support team wants to analyze chat logs to automatically identify the most common reasons for customer complaints and track how customer sentiment changes throughout a conversation. They plan to use prebuilt Azure AI Language features without any custom training. Which combination of features should they use?
medium- ✓ A.Key phrase extraction and sentiment analysis
- B.Entity recognition and language detection
- C.Text summarization and question answering
- D.Conversational language understanding and personal identification
Why A: Key phrase extraction identifies the most common reasons for complaints by pulling out important terms from the chat logs, while sentiment analysis tracks how customer sentiment changes throughout a conversation by assigning positive, negative, or neutral scores per utterance. Both are prebuilt Azure AI Language features that require no custom training, making them the correct combination for this scenario.
Variation 2. A customer support team wants to analyze chat transcripts to automatically extract the most frequently mentioned product issues and also determine whether each chat represents a positive, neutral, or negative customer experience. Which prebuilt Azure AI Language feature should they use?
medium- ✓ A.A. Text Analytics (prebuilt)
- B.B. Custom Text Classification
- C.C. Conversational Language Understanding
- D.D. Question Answering
Why A: The Text Analytics (prebuilt) feature in Azure AI Language provides pre-built capabilities for key phrase extraction (to identify frequently mentioned product issues) and sentiment analysis (to classify chats as positive, neutral, or negative). This matches the customer support team's requirements exactly without needing custom training or complex configuration.
Variation 3. A customer support team wants to automatically analyze incoming emails to (1) determine the overall emotional tone (e.g., frustrated, satisfied) and (2) identify specific key phrases that indicate the reason for contact (e.g., 'return item', 'refund policy'). Which two Azure AI Language features should they use? (Choose two.)
medium- ✓ A.Sentiment analysis
- ✓ B.Key phrase extraction
- C.Entity recognition
- D.Language detection
Why A: Sentiment analysis is correct because it evaluates text to determine the overall emotional tone, such as frustration or satisfaction, by assigning a sentiment score (positive, negative, neutral, or mixed) at the document and sentence level. Key phrase extraction is correct because it identifies the most relevant phrases in the text, such as 'return item' or 'refund policy', which directly map to the customer's reason for contact. Entity recognition identifies predefined entities like people or locations, and language detection determines the language, neither of which addresses the requirements.
Variation 4. A customer service team wants to analyze chat transcripts to understand customer sentiment and identify the most frequently discussed topics. Which two Azure AI Language features should they combine to achieve this?
medium- ✓ A.Sentiment analysis and key phrase extraction
- B.Language detection and entity extraction
- C.Text summarization and question answering
- D.Named entity recognition and translation
Why A: To understand customer sentiment and identify frequently discussed topics, the required features are sentiment analysis (to detect emotional tone) and key phrase extraction (to surface important terms/topics). Option A provides this pair. Option B (language detection and entity extraction) does not include sentiment analysis, so it cannot assess customer sentiment. Options C and D are also unsuitable because they lack sentiment analysis and do not directly address both requirements.
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.