ml-text-classifier

Tasks

1. Collect Data (Done 11/14)
2. Data Cleaning & Preprocessing (Done 11/18)
3. Data labeling (Done 11/29)
4. Model Training + Testing (Done 12/06)
5. Optimizing accuracy (Done 12/08)
6. Summary (Done 12/08)
7. Report (Done 12/08)
8. Presentation (Done 12/12)

Models completed so far: Logistic Regression, SVM, Neural Network using TFID

Project Maps

• DataCollection: project's input data
  • Stores our project's data
• Models: ipynb
  • logisitic regression model
  • NN model
  • SVM model
• Utils: Miscellaneous
  • script to crawl data from twitter api
  • scripts to do data cleaning: which were not used
  • scripts to gather sentiment analysis from AWS: (potentially) could be used to increased model accuracy as an additional feature