AI-102 Practice Question: Implement natural language processing solutions
You are a developer at a large retail company. The company receives thousands of product reviews daily. You need to build a solution that automatically categorizes reviews into positive, negative, and neutral sentiments, and also extracts key product features mentioned (e.g., battery life, screen quality) along with their associated sentiments. The solution must be scalable and cost-effective. You have access to Azure AI Language. You decide to use the built-in sentiment analysis and opinion mining features. However, after initial testing, you find that the opinion mining feature does not always correctly associate sentiments with the correct product features. For example, in the review 'The battery life is great but the screen is terrible', opinion mining might incorrectly associate 'terrible' with 'battery life'. You need to improve the accuracy of feature-sentiment association. What should you do?
⚠ Common exam trap
Test-takers frequently assume Azure AI Language's built-in opinion mining is fully reliable for all scenarios, but the exam tests the understanding that custom NER combined with post-processing is needed when the default model fails on complex multi-feature sentences.
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
✓
Create a custom NER project in Azure AI Language to extract product features, then use the opinion mining results and post-process to associate sentiments with the extracted features.
It combines Azure AI Language's built-in opinion mining with a custom NER model to extract product features, then uses post-processing logic to correctly associate sentiments with those features. This approach addresses the core limitation of opinion mining, which can misalign sentiments when multiple features with contrasting sentiments appear in the same sentence. By first extracting features via custom NER, you can then map each sentiment phrase to the nearest or most relevant extracted entity, improving accuracy without sacrificing scalability or cost-effectiveness.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Create a custom NER project in Azure AI Language to extract product features, then use the opinion mining results and post-process to associate sentiments with the extracted features.
Why this is correct
Custom NER can accurately extract the product features, and you can then use opinion mining scores to assign sentiment to each feature.
- ✗
Use the PII recognition feature to identify product features as entities.
Why it's wrong here
PII recognition is for personally identifiable information, not product features.
- ✗
Use Conversational Language Understanding (CLU) to define intents for each product feature and train a model with labeled utterances.
Why it's wrong here
CLU is for conversational flows, not for aspect-based sentiment analysis.
- ✗
Use the standard sentiment analysis API without opinion mining, and then use key phrase extraction to identify features and assign overall sentiment.
Why it's wrong here
This approach loses aspect-level sentiment granularity.
Go deeper
Related to this question
About these practice questions
One of 945 original AI-102 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 →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-102 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-102 exam.