A hybrid recommender system for patron driven library acquisition and weeding

Nowadays the explosion of information sources has shaped how library users access information and provide feedback on their preferences. Therefore, faced with this explosion and the blossoming of digital libraries, modern libraries must take up the challenge of meeting the needs of their users and considering their opinions and preferences in order to offer them adequate resources and henceforth eliminate those that are unsatisfactory. Almost all library recommender systems aim to provide users with items of interest to them. However, despite its definite interest, the staff-oriented adaptation and application of this revolutionary technique to the collection development process is still in an embryonic stage. We propose a patron-driven hybrid library recommender system that uses machine learning techniques to recommend and assist in the acquisition and weeding decision-making operations by extracting and analyzing users’ opinions and ratings. The recommender system is applied and validated in a real national library case using Amazon's digital library and the library's catalog as a data source. © 2020 The Authors