Sentiment Analysis with Opinion Mining in Azure AI Language
A customer service department wants to automatically extract the names of products mentioned in customer emails and the sentiment expressed about each product. For example, from the sentence 'The battery life of the X100 is excellent, but the screen is too dark,' they need to identify 'X100' and associate 'positive' sentiment with 'battery life' and 'negative' sentiment with 'screen'. Which Azure AI Language feature should they use?
Quick Answer
The answer is sentiment analysis with opinion mining, the correct Azure AI Language feature for this task. This capability goes beyond basic sentiment scoring by performing aspect-based sentiment analysis, which identifies specific opinion targets—like product names or features—and the sentiment expressed toward each one. In the example, it would correctly extract “X100” as the product, then link “positive” to “battery life” and “negative” to “screen,” matching the requirement to extract both the named entities and their associated sentiments from customer emails. On the AI-900 exam, this question tests your understanding of Azure AI Language’s advanced features; a common trap is confusing standard sentiment analysis (which gives an overall positive/negative score for the whole sentence) with opinion mining (which breaks sentiment down by target). Remember the memory tip: “Opinion mining = sentiment + target,” so if the task asks for both what is being talked about and how it’s felt, opinion mining is your answer.
⚠ Common exam trap
Candidates often confuse key phrase extraction (Option B) with sentiment analysis with opinion mining, because key phrases can include product names, but key phrase extraction does not provide any sentiment association, which is the core requirement of the question.
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 with opinion mining
Sentiment analysis with opinion mining is specifically designed to extract both the sentiment (positive, negative, neutral) and the associated target (e.g., 'battery life', 'screen') from text. This feature goes beyond simple sentiment scoring by identifying the opinion target and the sentiment expressed toward it, which directly matches the requirement to extract product names and their associated sentiments from customer emails.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Custom text classification
Why it's wrong here
Custom text classification assigns whole documents or spans to user-defined labels; it does not extract product entities or attach per-aspect sentiment. It is tempting because it is trainable on domain-specific categories, and it would be correct when the requirement is routing emails into bespoke buckets such as complaint or refund request rather than aspect-based extraction.
- ✗
Key phrase extraction
Why it's wrong here
Key phrase extraction returns salient noun phrases without linking them to products or assigning sentiment polarity. It is tempting because it surfaces terms like battery life and screen, and it would be correct when the requirement is simply summarising what a document discusses, not associating sentiment with each identified product aspect.
- ✗
Entity linking
Why it's wrong here
Entity linking resolves each mention to a knowledge-base entry such as a Wikipedia article, so it cannot attach per-aspect sentiment to 'battery life' versus 'screen'. It is tempting because it does identify entities, but that is for disambiguating names, not extracting opinions. The stem needs opinion mining with aspect-based sentiment analysis.
- ✓
Sentiment analysis with opinion mining
Why this is correct
Sentiment analysis with opinion mining returns both the overall document sentiment and the specific target and assessment pairs within it. That granularity links 'X100' to positive battery-life sentiment and 'screen' to negative sentiment, which plain sentence-level sentiment analysis cannot separate.
Go deeper
Related to this question
Learn chapter
Language Detection
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
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.
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 →
Same concept, more angles
2 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 retail company wants to automatically determine whether customer reviews are positive, negative, or neutral. Which prebuilt Azure AI Language feature should they use?
easy- A.Key phrase extraction
- B.Language detection
- ✓ C.Sentiment analysis
- D.Entity recognition
Why C: Sentiment analysis is the correct Azure AI Language feature because it is specifically designed to classify text into positive, negative, or neutral sentiment categories. This prebuilt capability analyzes customer reviews at the document and sentence level, returning a sentiment label and confidence scores, which directly meets the requirement of automatically determining review polarity.
Variation 2. 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?
easy- A.Key phrase extraction
- B.Language detection
- ✓ C.Sentiment analysis
- D.Entity recognition
Why C: 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.
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.