Introduction

ADAPT, or Automated Demographic Analysis of Physicists in Textbooks, is a tool that is capable of taking an input textbook and returning the list of scientists found in the textbook alongside their race, birth location, and gender. It utilizes a combination of database matching, named entity recognition machine learning methods, and scraping to accomplish this.

This site contains additional explanation on the methodology, benchmarks, and error for ADAPT. You can find a comprehensive explanation of how the physicist database was compiled, how the code pipeline works, the influence of error on outputs, as well as other pertinent information.

For additional info, you can contact me at txaa2019@mymail.pomona.edu