Link prediction for interdisciplinary collaboration via co-authorship network

TL;DR

This paper introduces a new link prediction method to identify potential interdisciplinary collaborations within a university's co-authorship network, based on analysis of publication data from the University of Bristol.

Contribution

The paper presents a novel link prediction approach tailored for interdisciplinary collaboration detection using co-authorship data.

Findings

Effective identification of potential interdisciplinary partners

Improved prediction accuracy over existing methods

Insights into collaboration patterns within the university

Abstract

We analyse the Publication and Research (PURE) data set of University of Bristol collected between $2008$ and $2013$. Using the existing co-authorship network and academic information thereof, we propose a new link prediction methodology, with the specific aim of identifying potential interdisciplinary collaboration in a university-wide collaboration network.