Facilitating interdisciplinary knowledge transfer with research paper recommender systems

Abstract Interdisciplinary knowledge transfer is hindered by information overload and siloed reading and citation practices. Research paper recommender systems, which tend to overemphasize similarity and relevance, can perpetuate information silos due to the “filter bubble” effect. In this work, we argue for the importance of offering novel and diverse research paper recommendations to scientists in order to reduce siloed reading and facilitate interdisciplinary knowledge transfer. We also identify important RP-Rec-Sys methodologies which serve this purpose. Specifically, we propose a novel framework for evaluating the novelty and diversity of research paper recommendations, drawing on methods from network analysis and natural language processing. Using this framework, we show that the choice of representational method within a larger research paper recommendation system can have a measurable impact on the nature of downstream recommendations, specifically on their novelty and diversity. We describe a paper embedding method that provides more distant and diverse research paper recommendations without sacrificing the relevance of those recommendations compared to other state-of-the-art baselines. By recommending relevant research to users that is distant and dissimilar from their own work, we present a viable method to facilitate interdisciplinary knowledge transfer using research paper recommender systems.