A network approach to expertise retrieval based on path similarity and credit allocation

TL;DR

This paper introduces a network-based method for automatically constructing researcher expertise profiles from publication data, demonstrating improved accuracy over traditional methods using the MEDLINE corpus.

Contribution

The paper presents a novel network approach utilizing path similarity and credit allocation for expertise retrieval, outperforming existing techniques.

Findings

Method applied successfully to MEDLINE corpus

Outperforms traditional expertise identification methods

Effective in constructing researcher profiles

Abstract

With the increasing availability of online scholarly databases, publication records can be easily extracted and analysed. Researchers can promptly keep abreast of others' scientific production and, in principle, can select new collaborators and build new research teams. A critical factor one should consider when contemplating new potential collaborations is the possibility of unambiguously defining the expertise of other researchers. While some organisations have established database systems to enable their members to manually produce a profile, maintaining such systems is time-consuming and costly. Therefore, there has been a growing interest in retrieving expertise through automated approaches. Indeed, the identification of researchers' expertise is of great value in many applications, such as identifying qualified experts to supervise new researchers, assigning manuscripts to reviewers, and forming a qualified team. Here, we propose a network-based approach to the construction of authors' expertise profiles. Using the MEDLINE corpus as an example, we show that our method can be applied to a number of widely used data sets and outperforms other methods traditionally used for expertise identification.