News Article Domain Classification

Problem Statement

In today’s world, data is power. With News companies having terabytes of data stored in servers, everyone is in the quest to discover insights that add value to the organization. With various examples to quote in which analytics is being used to drive actions, one that stands out is news article classification. Nowadays on the Internet there are a lot of sources that generate immense amounts of daily news. In addition, the demand for information by users has been growing continuously, so it is crucial that the news is classified to allow users to access the information of interest quickly and effectively. This way, the machine learning model for automated news classification could be used to identify topics of untracked news and/or make individual suggestions based on the user’s prior interests.

This project aims to develop a machine learning model that can classifies news articles into one of the five categories: business, entertainment, politics, sport, and tech. Given a new news article, the model should be able to predict which category it belongs to based on its content. This task is important for a variety of applications, such as organizing news articles for personalized news feeds, analyzing trends in different news domains, and detecting fake news. However, news domain classification is a challenging task due to the high variability in language and writing styles across different news domains, as well as the potential overlap between different categories. The goal is to develop a model that can overcome these challenges and achieve high accuracy in classifying news articles into their respective domains. All the models and data are tracked and maintained using DVC and MLflow.

Download the original dataset here : BBC News Classification Dataset
The dataset contains over 2,200 news articles from the BBC News website, covering five different topics: business, entertainment, politics, sport, and tech.
The articles were published between 2004 and 2005, and each article is labeled with one of the five categories.
The data at every transformation is uploaded and extracted from mongoDB database.
The dataset is split into two subsets: a training set and a test set.
Attribute Information

Article_ID: Unique identification key for a particular article.
Text: The text content of the news article.
Category: The category of the news article, which can be one of the following: business, entertainment, politics, sport, or tech.