I'm hoping to be able to examine the frequency of themes arising for an open ended question administered as part of a survey (n>1000). The answers are typically one to two lines of text. I'm hoping to identify a method and software package that will automate this process to some degree rather than coding by hand. Any help would be greatly appreciated. Thanks.
WBW,
TDC
I would suggest thematic analysis for the analyzing of the data. In terms of software, I have used Nvivo with great success. They have a trial you can try to see if it's a program that you think you can use for your data. I'm not sure if Nvivo will automatically code the data for you (I think not) but it's minimal word for coding that will also track and organize your themes.
Have you looked into text mining software packages? https://en.wikipedia.org/wiki/List_of_text_mining_software
I only have experience with coding by hand using Nvivo, which wouldn't be too onerous once you got into the swing of things.
Using Weka you will be able to, at least, automatically extract the different tokens (words) present in the answers and obtain the frequency of each token.
Data Reduction Techniques for Large Qualitative Data Sets
EMILY NAMEY, GREG GUEST, LUCY THAIRU, AND LAURA JOHNSON
https://www.google.es/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&ved=0ahUKEwj1jtDyqanNAhWLWxQKHaVvBFYQFgggMAA&url=http%3A%2F%2Fweb.stanford.edu%2F~thairu%2F07_184.Guest.1sts.pdf&usg=AFQjCNGXNsFGGgEB-fsQ-g90MZYGjAULng&sig2=F-hcOaflj0HVekvL6_IImA&cad=rja
You can look at the CRAN natural language processing task view:
https://cran.r-project.org/web/views/NaturalLanguageProcessing.html
Just copy all your answers (each ends with a period or question mark) into the text area of the page at http://rsp.itc.ntnu.edu.tw/SAMtool/SegWord_CGI.html and hit the submit button. It will list the terms (including phrases) and their occurring frequencies, relation links in a graph among the most 30 frequent terms, and a ranked list of your answers based on how many important terms each answer contains.
I am not sure if this fits your need, but you could have a try without effort.
Let me know what else you needs. I may have other tools for your application.
- Badges
- Science topic
- Similar topics
- Computer Science
- Data Mining