Web Scraping using BeautifulSoup and sentiment analysis using nltk
Harrison Kinsley has a Youtube channel by the name sentdex and he makes videos about python spanning across ML, AI, basic python, openCV, basic game programming etc. I aim to gauge the popularity of his videos based on Machine Learning from this ML playlist: https://www.youtube.com/playlist?list=PLQVvvaa0QuDfKTOs3Keq_kaG2P55YRn5v based on the Like to Dislike Ratio of the videos contained in this playlist
Once all the titles of these videos are scraped, I want to manually label these as good or bad videos based on their like to dislike ratio and then run a classification algorithm (Logistic Regression and Naive Bayes classifiers) to figure out the basics of natural language processing using Natural Language Toolkit in python aka nltk.
The code in Scrape_And_Analyze.ipynb is replete with comments where necessary and explains the intuition / thought process behind the steps executed in the notebook.
Refer these videos to learn BeautifulSoup and nltk basics in a jiffy:
BeautifulSoup: https://www.youtube.com/watch?v=zD0FDYI5_rs