Generalized Intelligent Framework for Tutoring (GIFT) (May 2018)
Adaptive training promises more effective training by tailoring content to each individual. Where non-adaptive training may be just right for one segment of the student population, there will be some students that find it too easy while others find it too difficult. Another, often ignored benefit of adaptive training, is improved training efficiency by minimizing the presentation of unnecessary material to learners. One implication of this is that intelligent, adaptive training should require less time to train a population of learners to a given level of proficiency than non-adaptive training. The gains in efficiency should be a function of several factors including learner characteristics (e.g., aptitude, reading ability, prior knowledge), learning methods employed by the adaptive training system, course content (e.g., difficulty and length, adaptability), and test characteristics (e.g., difficulty, number of items). This paper describes work in the second year of a three year effort showing the results of a predictive model for training efficiency based on those factors and how it could be integrated into the Generalized Intelligent Framework for Tutoring (GIFT) architecture. How this model supports return on investment decisions for authors is also discussed.
1 Army Research Laboratory
2 Charles River Analytics
For More Information
To learn more or request a copy of a paper (if available), contact James Niehaus.
(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)