Natural Language Processing with Yelp reviews data and building recommendataion system
Summary of analysis
Use NLP techniques, such as stemming, lemmatization and TF-IDF,to extract features from unstructured review text data.
Build language understanding models to classify positive and negative reviews using NLP techniques, Logistic Regression and Random Forests, being able to understand business performance based on user review text and comments.
Use unsupervised learning to cluster users into groups. Identify and understand the common user preference within each of the group by inspecting the cluster centroid.
Build a restaurant recommender system using collaborative filtering and matrix factorization based on user’s past visits and ratings.
Yelp reviews data
Yelp Data Challenge