In this project we are going to :
- Understand the theory behind sentiment analysis, including feature extraction from text (bag-of-words), and tokenizing
text (count vectorizer and term frequency-inverse document frequency) - Explore the Yelp Business Reviews dataset to perform text cleaning and vectorization
- Build Word Count and Word Cloud plots to extract some meaning from the sentiments
- Create a model to classify positive and negative reviews with Multinomial Naive Bayes Classifier, which is frequently used in the Natural Language Processing, as well as test your predictions