Modeling Behavioral Dynamics in Confidence-Based Assessment

Abstract

Confidence-based assessment is a two-dimensional assessment paradigm which considers confidence or expectancy level a student has about the answer, to ascertain his/her actual knowledge. Several researchers have discussed the usefulness of this model over traditional one-dimensional assessment approach, which takes number of correctly answered questions as a sole parameter to calculate the test scores of a student. However, very little is investigated about students' behavior in relation to different confidence-outcome knowledge regions. This Ph.D. research work aims to analyze and construct behavioral profiles of the students by focusing on their confidence level, performance, and navigation in a computer-based assessment system. The final goal is to provide a framework for an adaptive confidence-based assessment system which may be exploited to provide personalized feedback to improve students' confidence accuracy and knowledge by considering their behavioral dynamics.