Abstract:

This paper describes the design, implementation and assessment of an adaptive learning environment developed for undergraduate level organic chemistry students. This homework system is actively used by students who enrolled to two-semester undergraduate level general organic chemistry courses offered at Arizona State University (ASU). Its adaptive engine so called student model predicts student knowledge level on a given skill. This paper explains this adaptive homework system’s student model and used algorithm Bayesian Knowledge Tracing Model in a detailed manner. Paper also describes a small pilot study designed to give preliminary data on whether the adaptive version of this homework system has additional benefits to student learning over a non-adaptive version. A pilot study suggested that students who used the adaptive system may perform better than those who used an equivalent website that was not adaptive. The major contribution of this paper is the development of the adaptation algorithm and evaluation of its effectiveness on organic chemistry students.

Keywords:

Adaptive learning environment, Bayesian network, organic chemistry education, personalized learning, adaptive learning, STEM education.