USMA Admissions and Natural Language Processing
Abstract
The United States Military Academy (USMA) at West Point is renowned for producing Army Officers entrusted with the critical mission of leading Soldiers into combat. USMA expects each graduate to serve as a leader of character, prepared to lead Soldiers in the United States Army. Through data collected at USMA, this research provides a way to analyze the character of college applicants (prior to admission) using Natural Language Processing (NLP) techniques and machine learning algorithms. We extract NLP variables from letters of recommendation that were written about college applicants in an effort to predict the number of negative Cadet observation reports (NCOR) they receive per semester, which we use as a proxy measure for poor character. We provide evidence for a positive relationship between the number of NCORs that a Cadet receives per semester and recommendations with high average words per response and a higher than average proportion of negations. However, our results demonstrate that the approach of using basic NLP techniques is insufficient for admissions departments to achieve the very difficult task of assessing college applicants for downstream character issues.
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 10, 2023
- Accession Number
- AD1192986
Entities
People
- Evan W. Lee
Organizations
- United States Military Academy