ACRE: Automated Corpus Research Engine



Advised by David Walker

Apr 30, 2009

For my senior thesis, I created a project called ACRE (Automated Corpus Research Engine). This collection of programs autonomously downloads thousands of news articles daily, analyzes them using Latent Dirichlet Allocation, and then republishes those results on a website that I designed. The paper at right is the final writeup of the project and includes much of the rationale behind the project as well as information regarding how the program actually works.

The website can be found at

Related files:

Related links:

Final Report
Final report on the ACRE engine