A new framework of concept clustering and learning path optimization to develop the next-generation e-learning systems

Abstract

Most existing e-learning systems strictly require the course instructors to explicitly input the pre-requisite requirements and/or some relationship measures between the involved concepts/modules such that an optimal learning path as a sequence of the involved concepts can be determined for a class or an individual after considering the student's academic performance, educational background, learning interests, learner profile, learning styles, etc. In some cases, the learning path is determined solely by human experts. Since human can be biased, the course instructor's views on the relations of the involved concepts/modules can be imprecise or even contradictory, thus prohibiting any logical deduction of an optimal learning path. Besides, human experts may ignore or possibly be confused by contradictory requirements in the real-world applications. Therefore, we propose a new and systematic framework to develop the next-generation e-learning systems that will perform an explicit semantic analysis on the course materials to extract the individual concepts, and then grouped by a heuristic-based concept clustering algorithm to compute the relationship measures as the basis for extracting the prerequisite requirements/constraints between the involved concepts. Lastly, an evolutionary optimizer will be invoked to return the optimal learning sequence after considering multiple experts' recommended learning sequences which may contain conflicting views in different cases. It is worth noting that our proposed and structured framework with the seamless integration of concept clustering and learning path optimization uniquely represents the first attempt to facilitate the course designers/instructors in providing more personalized and 'systematic' advice (2014) 1(4): 335-352 DOI 10.1007/s40692-014-0016-8 through optimizing the learning path(s) for each individual class/learner. To demonstrate the feasibility of our prototype, we implemented a prototype of the proposed e-learning system framework, and also enhanced the original optimizer with the hill-climbing heuristic. Our empirical evaluation clearly revealed the many possible advantages of our proposal with interesting directions for future investigation.

Learning path adaptation in online learning systems

“…Some literature modeled the mapping process using constraint satisfaction problem [10,21] while others use mathematical models [7,22]. The course is then created by mapping the learning objects with student information.…”

“…The same way in the learning path adaptation, during minimizing each time phase of students attending learning objects, each student attempts a personal learning path by minimizing the relevance loss between consecutive learning objects along the path. The common method to formulate learning path problem in literature is to formulate as a constraint satisfaction problem (CSP) [10,19,21,25]. Constraint satisfaction problem consists of a set of precedence constraints (rules) and objective criteria.…”

“…The author [9] proposed the Forward Greedy algorithm to improve efficiency. In paper [21], the author proposes the hill climbing (HC) heuristic to find optimal learning paths for a group or individual learner. The proposed algorithm will iterate to apply either crossover and mutation operators until the solution is converged or the maximum number of generations is exceeded.…”

“…Specifically, the use of graph theory is not new in e-learning, however, there has been no formal model for discussing learning path problems based on graph theory. The works in the paper [21,29] defined a formal model for discussing learning path problems based on graph theory. The authors propose to address the problem of learning design recommendation in large repositories by reducing the problem space, then using a greedy algorithm.…”

“…However, this research is very complex due to various parameters involved in the adaptation process that causes the decision will become more complicated [21,32]. From the literature, the level of adaptation in learning path may be divided into three domains (Fig.…”