Madeline Coven is a PhD student at North Carolina State University who answered some about a recent project using natural language processing to visualize texts.
Please introduce yourself:
I am a digital humanist and an Education PhD student in the Learning Design and Technology program at NC State. While there, I want to make the most of the program to design new ways of teaching the humanities virtually, in a way that presents the nuances of ideas from philosophy and history. My latest work on text mining to this end is at madeline13 on GitHub.
How did you conceive of the project? What made you decide on visualizing philosophical texts using natural language processing?
It’s hard to think back when and how I conceived of this project. All I know is that it evolved out of a challenging but inspiring Quantitative Methods course at NC State. I wanted to see if there might be a way to standardize displaying the nuances of philosophical texts visually, as opposed to linking isolated words together in the conventional model.
What, if any, obstacles did your project face?
My only obstacle so far has been figuring how to display my data as a visualization in such a way that students can glean insight about philosophy by interacting with the visualization.
How has the project changed and evolved over the process?
Most of the project’s change and evolution will be in the future, as I test different visualization and insight-gleaning methods for the phrases I have tagged and extracted.
What’s next for the project?
I will now work on the proper visualization of my data, and apply my method of using single words to tag attached phrases, to develop a way of mining text from people’s stories (qualitative) for insight and nuance.
The software so far is at https://github.com/madeline13.
If you had to describe the project in 5 words, what would they be?
Hard-won, challenging, new for me, method, future