Embedding restaurant reviews
One common classification task that embeddings are great for is sentiment analysis. In this and the following exercises, you'll navigate through the workflow of performing sentiment analysis using embeddings.
You've been provided with a small sample of restaurant reviews, stored in reviews, and sentiment labels stored in sentiments:
sentiments = [{'label': 'Positive'},
{'label': 'Neutral'},
{'label': 'Negative'}]
reviews = ["The food was delicious!",
"The service was a bit slow but the food was good",
"The food was cold, really disappointing!"]
You'll use zero-shot classification to classify the sentiment of these reviews by embedding the reviews and class labels.
The create_embeddings() function you created previously is also available to use.
This exercise is part of the course
Introduction to Embeddings with the OpenAI API
Exercise instructions
- Create a list of class descriptions from the labels in the
sentimentsdictionary using a list comprehension. - Embed
class_descriptionsandreviewsusing thecreate_embeddings()function.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Create a list of class descriptions from the sentiment labels
class_descriptions = ____
# Embed the class_descriptions and reviews
class_embeddings = ____
review_embeddings = ____