Abstract:

In today’s world recommendations are ubiquitous. There are plenty of methods through which recommendations can be transferred, varying from word of mouth to recommender systems in which Artificial Intelligence (AI) technology is implemented. In this paper, we consider AI-supported recommender methods and call them Recommender Systems (RS). Due to the speed at which RS have advanced over the last few years, establishing an updated state of the art is significant. This document contains a systematic review aimed at delivering an objective overview of review on the topic of RS in the learning field. This review is developed using relative databases and a combination of related words as the search syntax. To obtain information about key findings, a qualitative content analysis was done minding the categories of relevant techniques used, effectiveness, quality standards and instructional applications, as well as main limitations and research gaps.

Initially, in this paper, a definition of RS will be provided, followed by a classification of types, features and ways to use data to help users. Furthermore, we will discuss the different data architectures of websites offering further education programs using RS. Finally, we will state the results of our investigation regarding existing gaps in the current state of the art and present suggestions for future research, as well as ways to improve RS in the field of further education.

Keywords:

Recommender systems, artificial intelligence, learning, further education.