The original_texts directory contains plain text versions of all 978 articles in the Southern Change Digtial Archive.

The modified_texts directory contains the 976 articles written in English and has substituted underscores for spaces in the most common phrases such as "affirmative action" and "civil rights.""

The stopwords.txt file is an expanded version of the default stop words provided by MALLET and includes common words in Southern Changes that bear little relevance to topical meaning.

The sc_model.R file is a script written in the programming language R. Using the modified_text files and the stopwords list, it creates a model similar to the one used in the website. It outputs a spreadsheet of the articles most representative of each topic as well as image files for topic wordclouds.

For working with R, the desktop application RStudio is highly recommended.