A Personalized Concept-driven Recommender System for Scientific Libraries

Abstract

Recommender Systems can greatly enhance the exploitation of large digital libraries; however, in order to achieve good accuracy with collaborative recommenders some domain assumptions must be met, such as having a large number of users sharing similar interests over time. Such assumptions may not hold in digital libraries, where users are structured in relatively small groups of experts whose interests may change in unpredictable ways: this is the case of scientific and technical documents archives. Moreover, when recommending documents, users often expect insights on the recommended content as well as a detailed explanation of why the system has selected it, which cannot be provided by collaborative techniques. In this paper we consider the domain of scientific publications repositories and propose a content-based recommender based upon a graph representation of concepts built up by linked keyphrases. This recommender is coupled with a keyphrase extraction system able to generate meaningful metadata for the documents, which are the basis for providing helpful and explainable recommendations.