The Dataset and Preprocessing techniques is copied from https://github.com/ahmadizzan/netifier/tree/master . The only part added to preprocessing is removing stopwords and stemming with Sastrawi. Also we modified remove_newline() function to do better for escaped character cases.
This project used Python 3.11 to develop the model
Library used in the projects :
- csv
- pandas
- numpy
- tensorflow
- matplotlib
- pickle
- re
- nltk
- Sastrawi