Arabic News Categorizer

5 Arabic news classification Models using TensorFlow. Takes user input through a GUI.

Models include + Credits:

1. CNN - Youssef Farag
2. SVM - Youssef Farag
3. HAN - Youssef Farag
4. KNN - Youssef Farag
5. Decision Tree - Mohab Abdulatif
6. LSTM - Ahmed Hossam
7. KNN - Ahmed Diaa

Evaluations:

1. CNN -> 0.98 accuracy
2. SVM -> 0.81 accuracy
3. HAN -> 0.92 accuracy
4. KNN -> 0.98 accuracy
5. Decision Tree -> 0.93 accuracy
6. LSTM -> 0.91 accuracy
7. KNN -> 0.94 accuracy

Classes include:

1. Politics
2. Entertainment
3. Economy
4. Sports

Running the project...

1. First download the dataset.
2. Run the main GUI file after updating paths.
3. You will have the option to train or classify.

*Make sure the generated x_model.h5 and word2vec.model path is hooked to the classify file.

OLD GUI:

New GUI: