Has anyone had any experience using CodeRead?

[mrdurtal]

I have found an interesting set of software tools written in Perl around 2001 by Andrew J. Perrin, a sociologist.

Before I get stuck into seeing what it can do and how, I thought I might ask if any PM has had experience using the software or knows of someone who has.

Perrin's article in Social Science Computer Review (The CodeRead System: Using Natural Language Processing to Automate Coding of Qualitative Data, 2001, 19:213-220) states the following:

This article suggests the use of some elementary techniques from the field of statistical natural language processing to partially automate the process of coding large quantities of free-form textual data. The article presents CodeRead, a set of tools that implement these techniques. The system's principal innovation is its ability to generate coding rules from a precoded sample of text. This capacity allows for the analysis of much longer textual data than was previously practical. It also insures that the rules used for coding such data are specific and uniformly applied.

Further info here: http://perrin.socsci.unc.edu/CodeRead/

There is evidence that the author has used his software for research purposes as recently as 2010.

A Super Search has produced nothing for "CodeRead". Thanks.

[ww]

Lack of update can be explained many ways -- hens have produced eggs in the same form for a bit more than the decade since Dr. Perin published CodeRead...and Perin himself has had other fish to fry (take a gander at his CV: the notion of 'publish or perish' comes to mind). However, the 1998-2001 CodeRead discussion on his UNC pages identifies some shortcomings ("not working very well" to throw out a PM bete noir) which suggest that if he was using it last year, he's also likely to have improved it.

his CV, http://perrin.socsci.unc.edu/cv.pdf strongly suggests that CodeRead was originally developed while he was a candidate for his PhD. His "computer tips" page suggests that he produced some interesting Perl s/w within the past few years... and provides an email address.

The academic world being what it is, an inquiry directed to him might be fruitful.

[Anonymous Monk]

suggests that he produced some interesting Perl s/w within the past few years... and provides an email address.

All good points

Yeah, contacting him could prove fruitful :)

[Anonymous Monk]

Here are some thoughts from an ignoramus

I doubt anyone here has even heard of it :)

If I were in your shoes, I probably wouldn't use it, as i can't find anyone besides the author using this on the internet, and it hasn't been updated since 2001, and it contains no sample data or test suite (example of usage).

Even though I'm not a sociologist or linguist, I still find the vocabulary tad akward.

Project - the whole document, coded. Why not call it document? CodedDocument? The there is a Pseudochunk ? Oh its made up of words,sentences,paragraphs,chunks :)

The linked article coderead-asa2000.pdf talks about this being more than mere natural language processing ... kinda reminds me of a tagcloud or Text::Categorize::Util ...

These nodes may interest you (some links to university projects with more than one person )

• general advice finding duplicate code
• Dutch Noun Phrases exctaction
• text mining text tokenizing
• NLP - natural language regex-collections?
• Natural language processing
• How to build a Search Engine.
• Perl NLP , PetaMem , http://nlp.petamem.com/
• Natural Language Sentence Production

[mrdurtal]

Excellent action!

Thanks for the links.

[mrdurtal]

Advice duly noted and contact shall be made!

BTW, CodeRead is apparently pronounced "code-red".