What to Use for Custom Offensive Terms in Azure AI Content Safety?
You have an Azure subscription that contains an Azure AI Content Safety resource named CS1. You plan to build an app that will analyze user-generated documents and identify obscure offensive terms. You need to create a dictionary that will contain the offensive terms. The solution must minimize development effort. What should you use?
Community Votes
100% of anonymous learners picked answer D. Votes are pick records left by other test-takers — they are not the verified answer.
Community Insight
The question tests the ability to choose the right Azure AI Content Safety feature for custom term filtering, where a blocklist is the low-code solution for custom dictionaries compared to training a text classifier.
To identify obscure offensive terms in user-generated documents with Azure AI Content Safety, you should use a blocklist. This page establishes that custom blocklists minimize development effort by allowing you to supply a custom dictionary of terms directly to the Content Safety API.
Choosing a text classifier (Option A) because it sounds like a custom AI model, but training a classifier requires significant development effort compared to simply uploading a list of terms to a blocklist.
Community Discussion (3 comments)
Comments & Corrections
No comments yet — spotted an error or have a note? Share it below.
Expert Analysis
Why the Answer Is Correct
A blocklist in Azure AI Content Safety allows you to define a custom dictionary of terms that the built-in models might not catch, such as obscure or localized offensive words. By simply adding these terms to a blocklist, the Content Safety service will automatically flag or block them during analysis. This approach requires minimal development effort since you only need to manage the list items rather than train and deploy a custom machine learning model.Why the Other Options Are Wrong
Option A, a text classifier, would require gathering training data, training a model, and deploying it, which involves significant development effort and is overkill for a simple term dictionary. Option B, language detection, merely identifies the language of the text and does not filter offensive terms. Option C, text moderation, is the built-in capability that detects profanity using default models, but it does not natively support adding custom obscure terms without integrating a blocklist.Community Comment Notes
Commenters highlighted that a blocklist is explicitly designed for custom dictionaries of offensive terms. As kennynelcon noted, "You can supply your own list of obscure or custom offensive terms as a blocklist". Another emphasized that blocklists are specifically designed for scenarios where predefined moderation models may not cover region-specific terms, minimizing development effort by integrating directly with the service.Official Reference
Exam Strategy
When a question asks to minimize development effort for custom term filtering in Azure AI Content Safety, look for the blocklist feature. Avoid options that suggest training custom models unless blocklists or built-in features are explicitly insufficient for the scenario.