Text Summariser

This is a text summariser that works on extractive method.

Steps

1. Use web-scraping to collect data from a web page
2. Clean the data
3. Tokenization
4. Remove stop words
5. Calculate the word frequency for each word
6. Calculate weighted frequency for each word
7. Calculate Sentence scores based on each word within sentence
8. Creation of summary with top 10 highest scored sentences

We will also compare extractive and abstractive methods to see which one fares better, in the future.

Sources

Inspiration for this code can be found here