Dynamic learning paths framework based on collective intelligence from learners

Abstract

Listen

Translate article

Learning maps allow learners to organize and personalize their learning materials, thus helping them to more effectively achieve their learning objectives. Accordingly, there has been ongoing research about learning maps with the goal of developing a comprehensive, easy to use, and powerful learning map. At present, the two most frequently used maps have either an ontological basis or take their design from the Petri net. These both provide a useful learning tool for learners. The ontology-based learning map represents integral concepts of knowledge and the relationships among concepts; however, it lacks the ability to control the learners' progress. The Petri net-based map can handle and personalize learning progress and designing the map is relatively easy, but its representation of the subject matter is relatively weak. The aim of this study is to design useful learning sequences and a representation interface that combine the above strengths. To do this, it offers the Dynamic Learning Paths Framework (DLPF), which is based on schema theory and the concept of collective intelligence. With the DLPF system, learners can provide feedback and contribute to a specific learning schema by submitting extra learning material. The self-improvement mechanism in the DLPF is designed to maintain the quality of learning materials to avoid the bias of collective intelligence. To evaluate the DLPF, questionnaires were developed and experiments to ascertain learning performance experiment were conducted. The results show that the proposed framework provides the well-organized learning materials, presents subject material effectively and can contribute to an improvement in learners’ academic performance.