rasyosef/amharic-news-classification

Deep Neural Network that classifies Amharic language news articles into 4 categories ('Business', 'International News', 'Politics', and 'Sport') with an f1-score of 0.87. # Amharic News Classification This project implements a Deep Neural Network that uses the amharic news dataset from here and a word2vec Amharic word embedding from here to classify Amharic language news articles into 4 categories ('Business', 'International News', 'Politics', and 'Sport') with an **accuracy** of **88%** and an **f1-score** of **0.87**. ## Code The `AmharicNewsTextClassification.ipynb` Jupyter Notebook contains python code for the entire process from loading and cleaning the data upto training the model. ## Result ### Classification Report ### Confusion Matrix