This project contains full code for 'How to scrap the news article from websites and their sentiment analysis'. Once scrapping is done, then we have used Lemmatization, Stemming, Vectorization techniques to analyze the sentiments and behaviors

For News Article scraping - The file 'NewsPapers.json' contains news website links. This file will be used in the 'News Data Scraping .ipynb' file. Once all the articles are scrapped, data will be saved into another csv file For sentiment analysis and Machine Learning - Run the file 'CSYE 7245- Big-Data Systems & Intelligence Analytics Project.ipynb'

1. I have published an article on web scraping using python on medium. Here is the link - https://medium.com/@ankurjain_79625/how-did-i-scrape-news-article-using-python-6eff936b3c8c
2. Here is the link of docker image - https://hub.docker.com/r/ankkur13/bigdatadockerimage/

Credit for the vast majority of support, tech-direction, course material and guidance here goes to https://github.com/nikbearbrown

For feedback and comments, please reach out to me at [email protected]