Attached you will find the provided data set and jupyter notebook to replicate the analysis.
We will be utilizing Text Data Vectorization for our sentiment analysis and using both Linear Regression and Random Forest for predictive modeling. If you have any questions or find areas for improvements, feel free to reach out.
Dataset can be found on Kaggle.
Analyzing and predicting customer satisfaction in Brazilian e-commerce. By understanding satisfaction in online market services and how it fluctuates on multiple parameters for both customers and sellers, we can determine the driving force and significant variables in contributing to both positive and negative reviews.