PREDICTING THE LEARNING PATH TO LEARNER’S OPTIMUM COMPREHENSION

Abstract

The essence of learning is for the learner to attain a significant level of comprehension after the learning process is completed. The quest to achieve this singular purpose has led to the introduction of several learning techniques  in the conventional learning environment, such as asking questions and conducting test after class, just to mention a few. Additionally, technology has been introduced in learning. Even with technological advancements, the learning experience still faces the challenge of learners not attaining the optimum comprehension state after the learning process. This is due to the present systems' inability to model the learner to determine the best methods for achieving maximum comprehension. Hence, this research paper focuses on deriving an improved mathematical model for predicting the learning path to a learner’s optimum comprehension. The paper presented three learning instructional media (learning paths); textual, audio and a hybrid of audio and video, which this research uses in modelling the learner. This is to enable the improved system predict the best learning path to optimum comprehension for learners. This research paper adopted Reinforcement Learning and the Markov decision process, specifically the Markov Chain approach, in developing an improved model for prediction. The evaluation of this research involved brainstorming on the Bellman’s equation with the aid of the Markov Chain transition state framework, resulting in an improved mean value function of 71.7. This indicates an enhanced comprehension state for the learning students compared to the existing mean value function of 46.0. The results obtained from this research clearly demonstrate that the improved model was able to predict and assign the best learning path to achieve optimum comprehension state for learners.