Mr. DLib: Recommendations-as-a-Service (RaaS) for Academia

TL;DR

This paper presents Mr. DLib's Recommendations-as-a-Service, enabling easy integration of recommender systems into academic digital libraries and reference managers, with a focus on content-based filtering and large-scale recommendation delivery.

Contribution

It introduces a new recommender service for academia, detailing its implementation, large-scale deployment, and future development plans for personalized recommendations.

Findings

Delivered 57 million recommendations to GESIS Sowiport

Implemented multiple recommender approaches including content-based filtering

Plans for integration into JabRef and establishing a living lab

Abstract

Only few digital libraries and reference managers offer recommender systems, although such systems could assist users facing information overload. In this paper, we introduce Mr. DLib's recommendations-as-a-service, which allows third parties to easily integrate a recommender system into their products. We explain the recommender approaches implemented in Mr. DLib (content-based filtering among others), and present details on 57 million recommendations, which Mr. DLib delivered to its partner GESIS Sowiport. Finally, we outline our plans for future development, including integration into JabRef, establishing a living lab, and providing personalized recommendations.