Courseiva
Implement natural language processing solutionshardMultiple ChoiceObjective-mapped

AI-102 Practice Question: Implement natural language processing solutions

Your company uses Azure AI Language to analyze customer feedback from surveys. The current pipeline extracts key phrases and sentiment. The data science team wants to identify emerging topics over time, such as new product complaints or feature requests. You need to modify the pipeline to track topic evolution. Which Azure AI Language feature should you enable?

⚠ Common exam trap

Microsoft often tests the distinction between prebuilt features (like key phrase extraction or NER) and customizable features (like custom text classification), leading candidates to choose a prebuilt option that cannot adapt to emerging, domain-specific topics.

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

Custom text classification

Custom text classification is the correct choice because it allows you to define and train a model to categorize feedback into custom classes (e.g., 'new product complaint', 'feature request') and track their frequency over time, enabling topic evolution analysis. Unlike prebuilt features, custom classification adapts to your specific domain and can be retrained as new topics emerge, directly supporting the data science team's goal of identifying emerging topics.

Answer analysis

Option-by-option breakdown

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

  • Named entity recognition (NER)

    Why it's wrong here

    NER identifies entities (people, places, organizations) but not abstract topics like product complaints or feature requests.

  • Conversation summarization

    Why it's wrong here

    Conversation summarization is designed for summarizing multi-turn conversations, not for analyzing individual survey responses or tracking topics over time.

  • Key phrase extraction

    Why it's wrong here

    Key phrase extraction extracts important terms but does not categorize them into topics or track evolution; it's not designed for topic modeling.

  • Custom text classification

    Why this is correct

    Custom text classification allows you to define topic categories (e.g., 'pricing complaint', 'feature request') and classify each survey response. By tracking classification frequencies over time, you can identify emerging topics.

About these practice questions

Courseiva writes every AI-102 question from scratch — 945 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 →

How Courseiva writes practice questions · Editorial policy

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.