Skip to content

alnbvy/BBCNewsClassifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

BBC news classification analysis using natural language processing

Deep learning prediction of BBC news articles using natural language processing.

Table of Contents

General Information

  • In this natural language processing project, I will a BBC news dataset from Kaggle BBC News Classification, which contains 2225 examples of news articles with their respective labels.
  • I am developing a model to perform classification of the BBC news articles into five categories: {1: 'sport', 2: 'business', 3: 'politics', 4: 'tech', 5: 'entertainment'}
  • In this project, I am utilizing a combination of the Embedding layer, GlobalAveragePooling1D and two dense layers to perform the classification
  • The project also contains pre-processing of the text corpus: tokenization, Sequences-truncating and -padding
  • The model achieves an accuracy of 95% on the validation set after 30 epochs.
  • Here is a snapshot of the training and validation loss during the training process.

Example screenshot Example screenshot

Technologies Used

  • Python
  • Tensorflow
  • Pandas
  • Matplotlib
  • Keras

Room for improvement:

  • Improvement could be made by doing transfer learning or using GloVe as a pre-trained embedding layer.

Contact

Created by Miralireza Nabavi - feel free to contact me!

About

Deep learning prediction of BBC news articles using natural language processing

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published