An experiment in computationally writing and compiling academic papers based around machine learning.

Currently working on:

• Automated scraping of academic articles

Completed:

• Initial user interface (web based) and initial hacky backed

• Set up Git repo (10/13/11)

Flow:

1. User enters a topic string. Ex) Canadian macro economic policy (Possibly add subtopics to refine search)
2. InstantPaper references online journal and academic sources and delivers a rating (0-100) on the availability of information on the chosen topic
3. Using a PageRank-esq algorithm, create a hierachy of academic papers based on imporance. Scrape content from top 100 papers on topics and using machine learning find commonly cited argument
4. Extrapelate 3-4 top 'themes' for each topic. These will act as individual body paragraphs
5. Rank indexed papers context and relevence to themes and add 5-6 'points' to each theme
6. Intelligently gather author information so we can get sentences like: "Scottish political economist Adam Smith wrote in the 'Wealth of Nations' that "arument/quote..." (Could also cross reference this information w/ Wikipedia)
7. Allow the user to select reference and citation format
8. Have a few other user settings: max word count, limit citations to 'n' length, user name, class, professor...etc.
9. Output as PDF/DOC/LaTeX