RajHarry / News-Article-Classification-BBC

Classifying the Given Article to one of the 5 classes in BBC Using the *BERT* ,*Glove* ,*ML* Algorithms

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

News-Article-Classification-BBC

Classifying the Given Article to one of the 5 classes in BBC Using the BERT ,Glove ,ML Algorithms

It is a public dataset from the BBC comprised of 2225 articles, each labeled under one of 5 categories: business, entertainment, politics, sport or tech.

The dataset is broken into 1490 records for training and 735 for testing. The goal will be to build a system that can accurately classify previously unseen news articles into the right category.

Classes information

Bar Chart

classes

Pie Chart

classes

Highly correlated words

classes

TSNE Data Visualization

data distribution

classes

Model Accuracies

Ml Algorithms

classes

Neural networks

classes

Neural networks with "Glove Embeddings"

classes

accuracy plot [NN-GLove]

classes

BERT Model

performance details

classes

About

Classifying the Given Article to one of the 5 classes in BBC Using the *BERT* ,*Glove* ,*ML* Algorithms


Languages

Language:Jupyter Notebook 92.6%Language:Python 7.4%