Ironhack Project NLP

Team 4 (Salva, Diego, Fabi)

This project investigates different machine learning models for text classification. The goal is to classify headlines as either "Fake news" or "Real news".

Files

• training_data_lowercase.csv: The dataset used for training and evaluating the models.
• main.ipynb: Jupyter Notebook containing the end result of our chosen model
• train.ipynb: Jupyter Notebook containing the code for data preprocessing, model training, and evaluation.

Instructions

1. Clone the repository.
2. Open main.ipynb in Google Colab or Jupyter Notebook.
3. Run the notebook cells to execute the code.

Results

The results of the different models and preprocessing techniques are summarized in the notebook.

Libraries

The following libraries are used in this project:

• re
• nltk
• numpy
• pandas
• matplotlib
• itertools
• sklearn

Make sure to install these libraries before running the code.

Contact

For any questions or feedback, please contact the team members.