skip to main content skip to footer

Computer Analysis of Essay Content for Automated Score Prediction: A Prototype Automated Scoring System for GMAT Analytical Writing Assessment Essays CAT GMAT

Burstein, Jill; Braden-Harder, Lisa; Chodorow, Martin; Hua, Shuyi; Kaplan, Bruce A.; Kukich, Karen; Lu, Chi; Nolan, James; Rock, Donald A.; Wolff, Susanne
Publication Year:
Report Number:
ETS Research Report
Document Type:
Page Count:
Subject/Key Words:
Computer Assisted Testing, Automation, Electronic Essay Rater (E-rater), Prediction, Graduate Management Admission Test (GMAT), Scoring, Essay Tests


For the set of 275 cross-validation data, exact or adjacent agreement with human rater scores reached 95%. For the 282 cross-validation issue essays, exact or adjacent agreement with human rater scores achieved 93%. The rich feature variables used as score predictors in the e-rater could potentially be used to generate explanation of score predictions, and diagnostic and instructional information.

Read More