- Course: Machine Learning Applications
- Final grade: 9.8/10
- Google Colab
- Rule-based and embedded transformers
- Topic modelling: LDA
The final result should represent the language used by each political party through visualizations, leading to a clear view on Spanish Political picture.
- Introduction
- Data Extraction: Twitter scraping and loading
- Training set: Preprocessing and Vectorization of tweets
- Testing set: Preprocessing and Vectorization of tweets
- Training and evaluation of the ML Model
- Comparison against pre-trained transformers (positivity and hate speech in rule-based and embedded transformers)
- LDA: topic modelling with gensim
- More data visualizations on political tweets
- Final conclusions
Contributions are welcome! Please fork the repository and submit a pull request with your changes. Feel free to customize it further to match your repository's specific details and needs!