newsscrape
news headline collecting for analysis in determining the category
newsscrape is web scraping for news headline to analyse on how it relates to a news category.
- It extracts RSS feed from Google News.
- Each news headline is matched against Google News category like Entertainment, Sports, etc.
- Called from scheduler to collect this data at 5 minutes interval and be accumulated in a database.
- It contains R statistical computing scripts to learn the pattern on words in the headline resulting a particular category.
- To test its accuracy in predicting...