news-data-scrapping-and-section-classification

This project scrapes news articles from a public news website, tags them using classification provided by the website, and uses a text classification model to predict article sections.

Getting Started

Prerequisites

• Python 3.9.13
• Install required libraries: pip install -r requirements.txt

Running the Script

1. Clone the repository: git clone https://github.com/Abhipawar02/news-data-scrapping-and-section-classification.git
2. Navigate to the project directory: cd news-data-scrapping-and-section-classification
3. Run the script: streamlit run main.py

Data Collection

• The raw data was collected from Public News Website.
• For detailed steps and code, refer to the News Website-Scrapper.

Data Preprocessing and Model Training

• Explore the steps, refer to the Scrapped News Data Preprocessing And Training

Model Evaluation

Note

• Both of notebooks could be find in /notebook directory

Results

• Inside /results-screenshots Directory

• Result-1

• Result-2

• Result-3