matitos_news/README.md

Matitos

• Scheduled tasks
  • Fetcher -> Inserts raw URLs
    • Fetch parsing URL host
    • Fetch from RSS feed
    • Fetch searching (Google search & news, DuckDuckGo, ...)
  • Process URLs -> Updates raw URLs
    • Extracts title, description, content, image and video URLs, main image URL, language, keywords, authors, tags, published date
    • Determines if it is a valid article content
  • Valid URLs
    • Generate summary
    • Classification
      • 5W: Who, What, When, Where, Why of a Story
      • Related to child abuse?
      • ...

Georgia Institute of Technology https://comm.gatech.edu › resources › writers

• Visualization of URLs

  • Filter URLs
    • By status, search, source, language
  • Charts

• Content generation

  • Select URLs:
    • Valid content
    • language=en
    • published_date during last_week
    • Use classifications
  • Merge summaries, ...