Skip to content

Latest commit

 

History

History
12 lines (10 loc) · 469 Bytes

README.md

File metadata and controls

12 lines (10 loc) · 469 Bytes

Tweet Classification

This project was done in the subject, COMP90042 (Natural Language Processing) taken in Semester1, 2020 in the University of Melbourne.

Text classification project: whether a tweet constitutes a rumour event

  1. Gather tweet messages from data
  2. Preprocessing
  3. Tokenization: MaxMatch algorithms
  4. Update the bag-of-words
  5. Feature extraction
  6. Hyperparameter tuning (classifiers: Naive Bayes and Logistic Regression)
  7. Compare performance