This machine learning project determines review ratings based on text reviews provided by previous visitors at universal studios. This project will look at polarity, as well as trends in the data that might hint to larger issues, such as frequency of negative words surrounding a certain ride or experience. The goal is to determine what factors make more loyal visitors, increase business, fame, brand value, and profit.
- Data Exploration
-
- numpy, pandas
- Pre-processing
-
- sklearn.preprocessing.MinMaxScaler
- Data Visualization
-
- matplotlib.pyplot, seaborn, wordcloud, texblob
- Classification Models
-
- KNN
- NLP Models
-
- NMF, LDA, TfidfVectorizer,
- Data modeling metrics
-
- confusion matrix, accuracy score, gains chart
- Python
- Jupyter Notebook
Data collected from Universal Studios will be used to determine how to create more satisfied customers.
- Python Code
Airline Passenger Satisfaction