This project focuses on the analysis of the Yelp dataset, which was previously introduced in the NLP section. The existing analysis of the Yelp dataset in our class remains incomplete, presenting an opportunity to explore alternative approaches for data analysis.
- Combine Multiple star reviews of 1,2 and 3 stars to make the data balance along with 4 and 5 star reviews. Then perform a classification using NLP.
- Another way to deal with data imbalance could be using a imbalanced data classification instead of combining multiple reviews.