Mine text on restaurant reviews
We aimed to build a binary classification model that will suggest a positive/negative review based on the data in the application. We split your data into two sets – 70% for training and 30% for testing. We then compared the results of three models such as, a Two-Class Boosted Decision Tree model, a Two-Class Logistic Regression model, and a Two-Class Neural Network model. Our goal in this exercise is to group the reviews into positive or negative reviews. You will use the Extract N-Gram Features to convert the unstructured textual data into numerical data to build the models.