Categories
Digital Humanities Text Analysis

Text Analysis Tools

I just ran across this very helpful index of text analysis and processing tools from the UT Scarborough library. Many of the tools mentioned have a web interface. Some have been deprecated, but I think it is still worth a look! https://find.digital.utsc.utoronto.ca/text_analysis. Please reach out if you know of a more current or comprehensive index.

Categories
Digital Humanities research Text Analysis Training

Text Analysis Instructional Videos

Constellate has now added 44 of their most-demanded instructional sessions to their YouTube channel: https://www.youtube.com/@Constellate_org. Check them out if you are looking for a way to start applying text analysis techniques to your research problem!

Categories
conference research

SQSP 2025

Marcus Charlesworth et moi sommes ravis d’animer la Table ronde 3 au Congrès annuel de la Société québécoise de science politique: https://sqsp.uqam.ca/congres/programme-preliminaire-congres-2025-uqam/

Categories
Digital Humanities France Text Analysis

Visualizing the Parliamentarians Project

We just finished performing optical character recognition on the recoverable sources from the Parisian Parliamentarians Project. Check out this nice interactive visualization of the source text. We will continue to organize the original scans and upload their .txt equivalents in the project repository.

Categories
ancient greece Publication research

Athenian Democratization

If you are interested in case studies of democratization, Polity has just released an article where I analyze the role of religious practices and institutions in normalizing a democratic transition: Democratic Civil Religion and the Kleisthenic Reforms.

Categories
research Technical

Machine Learning as a Research Tool

Here is a handy introduction to the basic principles of machine learning: Supervised vs Unsupervised Learning – What’s the Difference?. While reading it I paused to wonder whether there is any way to use machine learning for analyzing causal relationships. Machine learning automates the creation and evaluation of models but it doesn’t identify confounding variables, to run robustness checks, etc. I imagine that the predictions based on ML results tend to be rather conservative since they extrapolate the present to the future, rather than use a series of past events to identify root causes. Please feel free to correct me if there are already ML tools that have causal research functionality!