Learning Path Optimization Based On Multi-Attribute Matching And Variable Length Continuous Representation

Abstract

Personalized learning path considers both learner and resource attributes. The evolutionary algorithm approach usually forms the learning path generation problem into a problem that optimizes the matching degree of the learner and the generated learning path. The proposed work considers the learner attributes as ability level, learning objective, learning style, and expected learning time. The learning path attributes include difficulty level, covered concept, supported learning styles, required learning time, and prerequisites. A variable-length representation of the learning path is adopted based on floating numbers, which significantly reduces the encoding length and simplifies the learning path generating process. An improved differential evolution algorithm is applied to optimize the matching degree of learning path and learner. The quantitative experiments on different problem scales show the proposed system outperforms the binary-based representation approaches in scaling ability and outperforms the comparative algorithms in efficiency.

Generation of a Learning Path in E-Learning Environments: Literature Review

“…Apoki et al (2022) investigated the effects of including pedagogical agents in the Personalised Adaptive Learning System, particularly on predicted outcomes such as improved performance, task completion, increased motivation, and engagement. Xiao et al (2022) proposed an advanced differential evolution algorithm to optimise the degree of matching between the learning path and the learner.…”

“…Ontology in adaptive e-learning technology (Rahayu et al, 2022), with developing a recommender system based on ontologies and recommender methods for such systems, qualitatively adapts e-learning. E-learning systems (Xiao et al, 2022) provide a unique learning experience for each learner, with the proposal of a multiple attribute matching model (MAM) to describe the similarities between learner attributes and learning path attributes.…”

“…According to the researchers (Xiao et al, 2022), the number of materials has a limited impact on the quality of learning paths produced by VLCR (Variable Length Continuous Representation) algorithms. The high scalability of VLCR when it is combined with continuous evolutionary algorithms and the constant computation time of VLCR shows the potential for dealing with large-scale learning path planning problems, which might be essential for a real-world learning management system that contains thousands of learning materials to generate a valid learning path before the learner loses patience.…”