Which OCI language feature would help John categorize articles into topics like "politics," "technology," and "sports"?

Text classification is the correct choice in this context as it specifically relates to the process of categorizing text into predefined labels or topics. In John's case, he wants to organize articles under various categories such as "politics," "technology," and "sports." Text classification models are designed to analyze the content of the articles and assign them to these specific categories based on their contents, making it an ideal solution for this task.

In contrast, text generation involves creating new text based on a given prompt, which would not assist in categorizing existing articles. Text summarization focuses on providing a concise summary of a larger body of text, which again does not pertain to the task of categorizing. Text embedding refers to the process of converting text into numerical vectors for analysis or computation; while useful in many NLP tasks, it does not directly categorize articles into topics. Thus, text classification is uniquely suited for the task of topic categorization.