Extract Text and Sentiment Analysis in Azure Foundry
Short answer
Use Azure AI Document Intelligence (Vision) to extract text from the PDF files. Use Azure AI Language (Language) to perform sentiment analysis on the extracted text.
Question
You have a collection of press releases stored as PDF files.
You need to extract text from the files and perform sentiment analysis.
Which service should you use for each task? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Key Takeaways
Tests the distinction between Vision services (for visual/text extraction) and Language services (for semantic analysis like sentiment). The common trap is confusing Computer Vision with Document Intelligence or using a general AI model for structured text extraction.
Determines the correct Azure Foundry tools for extracting text from PDF press releases and performing sentiment analysis. Identifies Document Intelligence (formerly Form Recognizer) for OCR and Language Service for NLP tasks.
Common mistake: Learners often select 'Computer Vision' instead of 'Document Intelligence' because both handle images, but Document Intelligence is optimized for document-specific structures and high-fidelity text extraction from PDFs. Others might incorrectly use Speech Services for text-based sentiment.
Expert Analysis
Why the Answer Is Correct
For extracting text from PDF files, Azure AI Document Intelligence (found under Foundry Tools > Vision) is the appropriate service. It uses Optical Character Recognition (OCR) tailored for documents to extract printed and handwritten text accurately. For performing sentiment analysis on the extracted text, Azure AI Language (found under Foundry Tools > Language) is the correct choice, as it provides pre-built sentiment analysis capabilities that return positive, neutral, or negative scores.
Why Other Candidate Answers Are Wrong
Azure AI Speech is designed for audio-to-text transcription or speech synthesis, not for analyzing static PDF documents. Azure AI Search is used for indexing and querying data, not for initial content extraction or sentiment scoring. General Generative AI models can perform these tasks but are less efficient and more costly than specialized, purpose-built services like Document Intelligence and Language for these specific standard operations.
Community Comment Notes
As noted by user rokoskycloud, "The Read API is the OCR operation built for extracting text from images and PDFs," which aligns with Document Intelligence's capabilities. They also correctly identified that "Sentiment analysis is a Language service feature," confirming the need for the Language tool in the second step. This consensus highlights the importance of mapping specific data types (PDF vs Audio) and tasks (Extraction vs Semantic Analysis) to their dedicated Foundry tools.
Exam Strategy
Always match the input format to the service: PDF/Images go to Vision/Document Intelligence; Audio goes to Speech; Text semantics go to Language. In Foundry, check the 'Tools' section carefully as services are categorized by function.
Frequently Asked Questions
What is the difference between Computer Vision and Document Intelligence?
Can I use Generative AI for sentiment analysis?
Discussion 2 contributions
Compiled from public community threads and reader submissions, lightly edited for clarity. Handles and vote tallies are shown as recorded, and comments reflect the views of individual contributors.
From public community threads 2
-
8ac3742 👍 1extract: vision, sentiment and opinion: language Press releases are unstructured prose text (articles/announcements). In Microsoft's official curriculum and exam design, raw text/prose extraction from PDFs and images is handled by the Read API in Azure Vision. Why not Document Intelligence? Document Intelligence is specifically intended for structured/semi-structured form understanding (such as tables, key-value pairs, invoices, receipts, and tax forms). When the task is simply extracting plain prose for downstream NLP processing, Vision's Read API is the standard targeted service. Azure AI Language provides built-in text analytics capabilities, including Sentiment Analysis and Opinion Mining. Neither Vision nor Document Intelligence has sentiment analysis capabilities
-
rokoskycloud 👍 1Extract text: Azure Vision in Foundry Tools The Read API is the OCR operation built for extracting text from images and PDFs. Press releases are unstructured prose, so plain text extraction is exactly what's needed. Perform sentiment analysis: Azure Language in Foundry Tools Sentiment analysis is a Language service feature, returning document-level and sentence-level sentiment with positive, neutral, and negative confidence scores
Reader comments & corrections
No reader corrections yet — spotted an error or have a note? Share it below.
Related Analysis
Practice All AI-103 Questions
Access 88 questions with complete answers and detailed explanations.
View Full AI-103 Practice Test →