Data preparation
You are building a machine learning model that uses NLP for a sentiment analysis project that classifies restaurant reviews as positive, negative, or neutral. To prepare the data for training, you must preprocess and represent the text data numerically.
Your dataset contains thousands of reviews, one of which states:
"The food was delicious, but the service was extremely slow."
Which text preprocessing steps most likely remove the words "but" and "was" from this review?
This exercise is part of the course
Large Language Models (LLMs) Concepts
Hands-on interactive exercise
Turn theory into action with one of our interactive exercises
