AI FAQ for Confused Academics
A quick FAQ for academics and administrators making decisions about AI. 20 questions, 90% understanding, intentionally brief.
→ Blog
Thoughts on cultural analytics, data science, and digital humanities
ImageSpace: Using AI to Visualize Large Image Collections in the Browser
ImageSpace uses AI to turn any image collection into an interactive scatter plot. OpenAI's CLIP vision model generates embeddings, t-SNE arranges them by visual similarity, and HDBSCAN clusters them automatically—all viewable in the browser with no backend required.
Introducing tidylens: An R Package for Computational Visual Analysis
tidylens brings validated image and video analysis algorithms into the R tidyverse ecosystem, making computational visual culture research accessible to humanities scholars.
Switching to Astro with AI Help
Building a new website theme with Astro and AI tools. Turns out modern web development isn't as scary as I thought.
Announcing My New Book: Cultural Analytics in R - A Tidy Approach
My new book 'Cultural Analytics in R: A Tidy Approach' published by SpringerLink bridges humanities and computational methods.
Two New Publications: Topps Ripped and Programming Historian!
Announcement of two new published articles: one on Topps WWE trading cards and another on visualizing urban demographic data.
The GLM as a Means to Ensure Statistical Validity
Article published in the International Journal of Digital Humanities advocating for the General Linear Model and reproducible research compendiums.
Utilizing Time Series Analysis using Facebook's Prophet to Analyze Firearm Permits
Using Facebook's Prophet library to analyze time series trends in FBI NICS firearm background check data.
A Geospatial Analysis of Unaccompanied Migrant Children using Anselin Local Moran's I
Using spatial statistics (Anselin Local Moran's I) to analyze clusters and outliers in unaccompanied migrant children data.
Convolutional Neural Networks and HDBSCAN for Tagging Handwritten Archival Material
Using CNNs and HDBSCAN clustering to automatically categorize handwritten archival materials from the CWRGM project.