Data mining, crowdsourcing, and content analysis

Hi everyone,

My background is in professional communication and technical writing (among other things). Currently (Thurs, 3/22/2012) I’m here at ATTW/CCCC in St. Louis giving a presentation. The project I’m working on uses politeness theory to help analyze email messages from the Enron email corpus. This project introduced me to research in corpus studies, computational linguistics, and digital humanities.

Part of the project included the use of Google Docs to crowdsource the sampling and coding of 400 email messages for the project.  Amazing to me was the fact that these 400 messages were identified and coded using 20 student volunteers to code the data over a single weekend.

Through this project I’ve realized how much data and how many tools are out there. Tools and data that would be helpful for those of us in the humanities if only we had a little technical know-how or guidance to get us started.

I’d love to share my experience and connect with others who have experience or are interested in learning more or even helping to develop resources or research ideas.

Please feel free to contact me at christon.walker(at)usu(dot)edu. You can also click here for access to the presentation slides for my ATTW presentation on politeness and study of the some of the Enron email corpus.

Categories: General | Tags: , , , , |

About chris w

I'm a PhD student in the Theory and Practice of Professional Communication program at Utah State University. I'm interested in a wide range of things, but my research interests generally center on technology and community. I would love to talk with others interested in data mining and "Web 3.0", digital humanities, content analysis, crowdsourcing, DIY/hacker/maker/craft cultures.