Personalizing and improving e-learning system using roulette wheel selection algorithm, reinforcement learning and case-base reasoning approach Conference Paper uri icon

abstract

  • Despite the ever-increasing practice of using e-learning in educational institutions, most of the applications perform poorly in motivating students to learn for many reasons and varied factors. Online educational materials make learning a task-driven process but can be improved by providing a personalized topic sequencing that match the learner’s ability, background and prior knowledge. By improving, optimal teaching operation in e-learning system can be achieved by bringing the learner closest to the ultimate learning goal. This can be achieved by employing evolutionary technique; roulette wheel algorithm (RWA), reinforcement learning (RL) and case-based reasoning (CBR) approach. This paper makes three critical contributions in e-learning development and implementations: (1) it presents a personalized topic sequence using the roulette wheel selection algorithms; (2) provides reinforcement learning through practice and mastery learning and; (3) to illustrate case-based reasoning approach in retrieving and storing cases for further use and profiling students.

publication date

  • July 2013

keywords

  • personalized learning sequence, e-learning, reinforcement learning, mastery learning, theme analysis

start page

  • 184

end page

  • 193