Recommender Systems: Taxonomy, Applications and Current Research Trends

Abstract

Recommender Systems play an essential role in assisting users to navigate the immense amount of information and services available online, aiding them in the decision-making process and adding a lot to the overall user experience. However, the rapid advancement and widespread adoption of technology have ushered in a framework in which enormous amounts of data (complex and heterogeneous) are available from different information sources (such as Internet of Things or social networks). This vast amount of information has led to develop advanced techniques in recent years that offer great opportunities and challenges for business, education, health, and other domains, making more accurate and personalized recommendations, providing explanations that capture the multifaceted information underlying recommendations and clarify their generation, and allowing the performance of the systems to be adequately assessed. This work provides an overview of theoretical research and practical developments in recommender systems, based on the Web of Science and following the guidelines for systematic literature reviews in software engineering. It aims to present a well-defined framework that allows students and researchers without a strong background in the field to easily identify current issues and develop new and significant advances. To this end, a comprehensive and practical taxonomy is first proposed based on two criteria, the recommending approach and the target users. This is followed by a report of recent practical developments, free/open source recommender systems software, and a snapshot of the status of publications, in order to unravel current research trends. And finally, some potential and significant future research directions are presented to assist interested researchers make significant advances in the area.