Learning object recommendation for an effective open e-learning environment
Ganesh Venkataraman, Chellam Srinivasan, Arunkumar Ravichandran, Susan Elias, Lakshimi Prabha Ramesh · 2015
Over the past few years, with the exponential expansion of the World Wide Web and its applications, there has been a paradigm shift in the way people learn — Massively Open Online Courses (MOOCs) and other online learning recourses are fast replacing conventional textbook learning. Efforts are also being made to develop and foster crowd sourced massive open repositories of learning objects, which can be tapped to author courses for diverse learners with varied backgrounds dynamically. While this can be done by adopting different systems and architectures, its effectiveness calls for a collaborative approach of learning object recommendation, driven by the learner's learning preferences. A course is basically authored based on the learner's requirements by retrieving learning objects that have high aptness to the particular subject/course and high collaborative-predicted rating which signifies high relation to the user's learning preferences. The learner rates the content after working on the learning object and this rating is used to learn the aptness and the learner's preferences.