I’m happy to report that a paper of mine (in collaboration with David E. Williams at the University of Saskatchewan) has just been published in The Internet and Higher Education. We topic modeled 77,514 tweets from 59 academically-themed but anonymous or pseudonymous Twitter accounts. This resulted in five broad topics, and we followed up with a qualitative analysis of the 100 most-representative tweets from each of those topics to generate some narrower codes.

Just because you can topic model something doesn’t mean it actually tells us anything (and please don’t ever describe computational text analysis as “objective”).