Automated Scoring

The increased use of constructed-response tasks — test questions that elicit student-produced responses, such as short written answers, essays and recorded speech — has created a need for innovations that allow for valid, reliable, timely and cost-effective results. ETS has been involved in research on the automated scoring of open-ended tasks for 25 years.

In response to the states' desire to consider automated scoring as a means for helping achieve valid and efficient measurement of abilities using constructed-response items, ETS, along with collaborators Pearson and the College Board, have written the white paper Automated Scoring for the Assessment of Common Core Standards. Our goal is to create methods and computer applications that reduce the cost and effort involved in using human graders while improving the validity of test results.