AI-102 Practice Question: Implement natural language processing solutions
You need to analyze the sentiment of social media posts in real time using Azure AI Language. Which approach should you use?
⚠ Common exam trap
Watch out — candidates often confuse real-time processing with streaming architectures (like Event Hubs and Stream Analytics) or batch processing, but the simplest and most direct real-time approach for per-document sentiment analysis is the REST API.
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
✓
Call the sentiment analysis REST API for each post
The sentiment analysis REST API in Azure AI Language is designed for real-time, per-document analysis. By calling the API for each social media post as it arrives, you achieve the lowest latency and can process posts individually without batching or streaming overhead, which is essential for real-time sentiment analysis.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Call the sentiment analysis REST API for each post
Why this is correct
The sentiment analysis REST API processes each post synchronously, returning polarity scores immediately, which satisfies the real-time constraint. Batch or asynchronous pipelines would introduce latency, so per-post API calls are the appropriate mechanism for streaming social media sentiment.
- ✗
Use Azure AI Search with cognitive skills
Why it's wrong here
Azure AI Search cognitive skills enrich content during indexing, which is batch-oriented and lags ingestion, so real-time sentiment on arriving posts is not delivered. It tempts because it invokes Azure AI Language skills; it would be correct for enriching a searchable corpus, not live scoring.
- ✗
Use the batch processing feature in Azure AI Language
Why it's wrong here
Batch processing submits jobs that return results after completion, so sentiment is not produced as posts arrive. It tempts because it uses the same Azure AI Language sentiment capability; it would be correct for scoring a stored dataset, not a real-time social media feed.
- ✗
Send posts to an Event Hub and use Stream Analytics
Why it's wrong here
Stream Analytics performs SQL-like windowed queries over Event Hub streams but does not itself call the Azure AI Language sentiment endpoint, so posts are routed without being scored. It tempts for high-throughput ingestion; it would be correct when the requirement is stream aggregation, not sentiment analysis.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-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-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.