/Article-Categorization

Categorize unseen articles into 5 categories namely Sport, Tech, Business, Entertainment and Politics

Primary LanguagePython

Article-Categorization

Python NumPy SciPy Pandas scikit-learn Keras TensorFlow Plotly Kaggle

Description

This project's goal is to group previously unknown articles into five categories: sport, technology, business, entertainment, and politics. The BBC text data, which contains more than 2000 articles, is used to train a deep learning model using bi-directional LSTM layer.

How to Run the Project

  1. Clone the repository
  2. Open the directory
  3. Locate the Train.py inside the previous directory of the cloned repository
  4. Run the file on your chosen IDEs
  5. If done correctly, this will generate the results

Neural Network Model Plot

model plot

Model Performance on The Test Dataset

Model Training/Test Accuracy plot

acc

Model Training/Test Loss plot

Loss

Tensorboard plot

tensorboard

Classification Report

class report

Confusion Matrix display

confusion_matrix

Credits