Things I have been working on:
Python:
Audio transcript converter for the Texas English Linguistics Lab.
Clustering texts for my dissertation.
Corpus tools developed for the Texas German Dialect Project.
Converting subtitles from Youtube for automatic vowel measurement, for a study on political speech in the U.S.
A tweeting speech bot (lives here) and tools for the Digital Writing and Research Lab. Described in this blog post.
Analyzing language use in the Republican debate, for the Digital Writing and Research Lab's blog.
Identifying non-English online postings, for my dissertation research.R:
Surveytools, a R library for survey analysis. This was used for the Mechanical Turk perception study in my dissertation.
Vowel normalization and plotting with ggplot, for research on vowel changes in Canada.
A script for advanced vowel plotting in ggplot2, for the Texas English Linguistics Lab.
Exploratory plotting and statistics, for research on consonant retraction in Texas.
Things I have written:
Text processing in Python: some basics
Contact:
Here be my LinkedIn.