Machine Analysis of Free Text Answers

These files represent the breakdown of responses to free text questions.  

This is all preliminary and there is no statistical analyis provided at this time. 

Provided for each question are two files, the first labled "XXX_analysis.txt" contains the 20 most common bigrams and trigrams; as well as the 20 most frequenly used words in the responses.

The second file, XXX_concordance.txt contains a look at each of the top 5 words in context.

If you have experiance with Natural Language Processing (paticularly in Python) and want to help us do a better job of analyzing the responses, please email Wade