REFORE: A recommender system for researchers based on bibliometrics

Recommender systems (RSs) exploit past behaviors and user similarities to provide personalized recommendations. There are some precedents of usage in academic environments to assist users finding relevant information, based on assumptions about the characteristics of the items and users. Even if quality has already been taken into account as a property of items in previous works, it has never been given a key role in the re-ranking process for both items and users. In this paper, we present REFORE, a quality-based fuzzy linguistic REcommender system FOr REsearchers. We propose the use of some bibliometric measures as the way to quantify the quality of both items and users without the interaction of experts as well as the use of 2-tuple linguistic approach to describe the linguistic information. The system takes into account the measured quality as the main factor for the re-ranking of the top-N recommendations list in order to point out researchers to the latest and the best papers in their research fileds. To prove the accuracy improvement, we conduct a study involving different recommendation approaches, aiming at measuring their performance gain. The results obtained proved to be satisfactory for the researchers from different departments who took part on the tests. (C) 2015 Elsevier B.V. All rights reserved.