TOWARD INTELLIGENT ASSESSMENT: AN INTEGRATION OF CONSTRUCTED RESPONSE TESTING, ARTIFICIAL INTELLIGENCE, AND MODEL‐BASED MEASUREMENT

Abstract

A new assessment conception is described that integrates constructed‐response testing, artificial intelligence, and model‐based measurement. The conception incorporates complex constructed‐response items for their potential to increase the validity, instructional utility, and credibility of standardized tests. Artificial intelligence methods are invoked to produce item‐level partial‐credit scores and diagnostic analyses similar to those of a human expert. Finally, cognitively‐grounded measurement models provide diagnostic statements based on commonalities in performance across items. Progress toward achieving this conception is examined, with emphasis on two automated scoring programs. Potential applications of intelligent assessment are discussed.