Collaborative E- Learning Algorithm for Domain Knowledge Acquisition using Unbiased Matching
Authors:
EZE Monday
Publication Type: Journal article
Journal: International Journal Of Scientific And Research Publications
ISSN Number:
0
Downloads
20
Views
Abstract
The need to acquire domain knowledge at a fast pace cannot be overemphasized. Domain knowledge acquisition is not limited to any particular field, but rather, is a requisite path to giant strides in the sciences, technology and academics. Apart from being a major goal at all levels of academics, knowledge acquisition is inevitable in some fields of computing such as Artificial Intelligence and Expert Systems, where system construction is hinged on the ability of the system developers to elicit knowledge from the domain experts. Collaborative e-learning is a positive deviation from the traditional learning paradigm, in that knowledge is shared between the participants, through information technology. However, one of the challenges of collaborative learning is how to organize the team of learners, so as to maximize the learning impacts. Another important issue is, how to device empirical strategies, for measuring the impact of e-learning methodologies. This work proposes a collaborative e-learning algorithm called the Community Bi-Partition Learning Model (CBLM). The algorithm applies a computational technique known as unbiased matching, to partition a learning community in order to speed up the process of knowledge acquisition. A validation approach for measuring the impact of the e-learning algorithm is also presented.