Skip to content

Latest commit

 

History

History
4 lines (4 loc) · 349 Bytes

README.md

File metadata and controls

4 lines (4 loc) · 349 Bytes
  • Performed a sentiment analysis using BERT and roBERTa to predict the emotion of tweets about coronavirus
  • Realised a basic Naive Bayes classifier to serve as a benchmark for the two models, with accuracy around 70%
  • Produced remarkable results, with both models yielding around 90% accuracy and F1 scores, significantly surpassing the benchmark