Your question is Engineer Features for Text Classification. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
You are building a text classification model for a product that routes incoming messages into a small set of labels. The text is noisy, short, and often includes slang, misspellings, emojis, and product-specific terms. You need to decide which text features to create, how to preprocess the text, and how to balance sparse features with embedding-based features.
How do you approach feature engineering for a natural language processing task?