Scrap open-access Nature articles and store them as txt files.
- User can specify which year's articles to scrape/analyze
- User can specify maximum word count per word per article to reduce over-counting
Scrape articles using Beautiful Soup and store them as text files
Parse scrapped articles and sum up word counts
Clean common words and other baised words
A better approach to cleaning scraped data using TF-IDF, document frequency analysis and z-score outlier detection