REAL WORLD USAGE OF AN ADAPTIVE TESTING ALGORITHM TO UNCOVER LATENT KNOWLEDGE
Danny Lynch, Colm P. Howlin · 2014
Abstract At the beginning of every course, it can be expected that several students already have some knowledge of the curriculum. For learning efficiency it is important to quickly identify this latent knowledge. This enables students to begin new learning immediately which in turn prevents the frustration or boredom that might be caused otherwise. A component of the Realize it learning environment that uncovers this latent knowledge is an algorithm called Determine Knowledge . This is offered as an adaptive pretest at the beginning of each course. It allows new students to be automatically placed at the appropriate position within the course. In this paper, we detail the algorithm and review its relative strengths and weaknesses. In particular we discuss the real-world usage of Determine Knowledge run in a higher educational institute in the United States over a two year period. In total this encompasses over 455,000 Determine Knowledge operations performed by over 48,500 unique students. We finish the paper by outlining some of the enhancements made to the algorithm based on the analysis of this data. Keywords: Latent Knowledge, Technology Enhanced Learning, Intelligent Learning Systems.