Latent Dirichlet Allocation in R

This repository contains the code of my 2012 thesis (http://epub.wu.ac.at/3558/1/main.pdf).

@STANDARD {,
    title       = "Latent Dirichlet Allocation in R",
    institution = "Institute for Statistics and Mathematics, WU (Wirtschaftsuniversität Wien), Austria",
    author      = "Martin Ponweiser",
    language    = "English",
    type        = "Diploma thesis"
    year        = "2012",
    url         = "http://epub.wu.ac.at/id/eprint/3558"
  }

Folders:

• application-pnas: LaTex/Sweave/R code of the main part of the thesis. Also included are the PNAS abstracts corpus and metadata in tm format.
• dirichlet: Sweave/R code to generate figures of the beta and Dirichlet distributions
• web-scraping: a Python/Scrapy/R project to web-scrape a corpus of PNAS journal abstracts