Stat 628 Module 2 --- Sentiment Analysis on Yelp Data

We are Tuesday Group 3. Our team members are Siyu Wang, Xiaohan Wang, and Tiannan Huang.

Our Analysis contains two parts:

1. Kaggle prediction: Predict the star of each review base on the review content.
2. Business Analysis: Give some specific ideas to the business owner.

File Summary

yelp_final.ipynb: Our final jupyter notebook about this project

yelp_final.pdf: PDF generated by yelp_final.ipynb

code folder

628proj2.twb: Tableau file for presentation1 plots

Business_analysis.py: python file for business analysis

Kaggle.py: for Kaggle prediction

Stat628.R: R file for some hypothesis testings and ggplots

data folder

generated data folder: some intermediate data generated in the process

opinion-lexicon-English folder: positive and negative dictionary by Minqing Hu and Bing Liu

Submission: contains our four submission for Kaggle prediction

image folder

Kang's Idea.jpg: Professor Kang gives us some suggestion on this project

presentation1 & presentation2: plots for presentation

presentation folder

628_proj2_ppt1.pptx & 628_proj2_ppt2.pptx: for presentation1 and presentation2