logo

LSTM News Categorizer

2021
247 views
favouite

0

1

2

3

4

5

6

7

8

9

 Favourites
slider-arrow
slider-arrow
slide-image

LSTM News Categorizer

2021
247 views
Project details

There are many sources of news. 

Sometimes you want to read news by a specific category (for example, just Sports and|or Business). 

Some news resources don't have news categories or their grading is rather arbitrary. 

Our client came up with the idea of a news aggregator that they would like to see in their app. 

The concept of the aggregator is a model that categorizes the news text from several sources into 10 topics: 

  • World, 
  • Health, 
  • Society, 
  • Incidents, 
  • Politics, 
  • Sports,
  •  Business, 
  • Culture, 
  • Economics, 
  • Technology. 

Classification models were trained for two languages: Russian and Kazakh. 

The news language is detected by a model based on a perceptron, which was trained on the collected data of Russian and Kazakh

The categorizer model is based on the LSTM (long short-term memory) neural network. In practice, the model has shown a good quality of news categorization (validation accuracy more than 0.93), provided it is multi-label and multi-category.

Tags
#ml
#tensorflow
#python
Technologies
#Python
#TensorFlow
#ML

Similar works