This project explores the performance of various classification models for text using Twitter and news datasets. We collected three datasets: a multi-class dataset of tweets collected using the Twitter API with ten different classes, a binary classification dataset of US election-related tweets sourced from Kaggle, and a news article dataset obtained from Python's Sklearn library with varying lengths compared to the Twitter dataset.
To run the code in this project, you'll need the following dependencies:
- Python 3.x
- Scikit-learn
- Tweepy
- Pandas
- Numpy
- Matplotlib
- Keras
- Tensorflow