IMPROVING USER EXPERIENCE IN LIBRARY SYSTEMS THROUGH RECOMMENDER TECHNOLOGIES

Abstract

Recommender systems are efficient tools for filtering and organizing information in library information systems, which is increasingly critical due to the growing reliance on digital resources, personalization trends, and the widespread adoption of online library services. While modern recommender systems are highly effective in providing accurate suggestions tailored to user needs, they encounter various limitations and challenges, such as scalability, the cold-start problem, data sparsity, and integration complexities. The diverse array of techniques available for building recommender systems further complicates the selection process, especially when designing systems to meet the unique needs of library users. Each technique offers specific features, advantages, and disadvantages, raising questions that require careful consideration when applied to library environments. This paper aims to provide a systematic review of recent advancements in recommender systems within the context of library information systems, focusing on their applications for recommending books, academic papers, journals, multimedia resources, and other library assets. First, the paper examines the various ways recommender systems are utilized in library settings to enhance the user experience by delivering relevant resources based on user preferences, search behavior, and historical interactions. Next, an algorithmic analysis of different recommender system techniques such as collaborative filtering, content-based filtering, hybrid methods, and machine learning approaches is conducted, and a taxonomy is developed to outline the essential components required for designing an effective library recommender system.