Preparation of Recommendations on the Selection of Educational Resources for Different Learning Styles

Abstract

Introduction. Lifelong learning is now an important part of personal and professional development, as the internet offers a wide variety of e-learning content. However, students often need advice or recommendations for finding learning resources based on the experiences of students who have already taken these courses or used these resources. Such advice can be obtained from a recommender system that will provide intelligent support for e-learning during lifelong learning. The authors are interested in developing such a system. The task of generating recommendations during learning is aimed at improving the acquisition of knowledge and skills. This can help students select learning resources based on their learning style and goals. Therefore, developing a recommender system that can automatically generate recommendations for selecting learning resources for a specific user, taking into account their preferred delivery style, is a relevant task.

The purpose of the paper is to propose a methodology for generating recommendations for resource selection based on learning style, thereby improving the ease and quality of learning.

Methods To account for learning styles, the Felder-Silverman model was chosen. It describes four scales that determine student learning advantages: active/reflective, sensory/intuitive, visual/verbal, and sequential/global.

Results. Lifelong learning is becoming increasingly popular, as it enables people of all ages to learn for various purposes, whether for earning a degree or simply refreshing their knowledge in certain subjects. A methodology is proposed for developing recommendations for selecting learning resources using specific situations that might be encountered by someone seeking to learn with different learning styles, such as audio, text, and so on. A structural diagram of the recommender system is presented, which will enable the development of such recommendations for lifelong learning, taking into account accumulated learning experience in sim ilar situations.

Conclusions. The methodology proposed by the authors allows, based on descriptions of a set of resources provided by developers, to suggest to students the three most suitable resources that match their desired learning style. Future research will focus on implementing the proposed recommender system and testing it in specific use cases, providing tailored recommendations for various learning purposes.