ReCiter: An open source, identity-driven, authorship prediction algorithm optimized for academic institutions.

Paul J Albert,Terrie R Wheeler,Drew Wright,Zimeng Zhu,Mohammad Mansour,Jie Lin,Michael Bales,Curtis L Cole,Sarbajit Dutta,Stephen B Johnson,Cassidy R Sugimoto

doi:10.1371/journal.pone.0244641

Abstract

Academic institutions need to maintain publication lists for thousands of faculty and other scholars. Automated tools are essential to minimize the need for direct feedback from the scholars themselves who are practically unable to commit necessary effort to keep the data accurate. In relying exclusively on clustering techniques, author disambiguation applications fail to satisfy key use cases of academic institutions. Algorithms can perfectly group together a set of publications authored by a common individual, but, for them to be useful to an academic institution, they need to programmatically and recurrently map articles to thousands of scholars of interest en masse. Consistent with a savvy librarian’s approach for generating a scholar’s list of publications, identity-driven authorship prediction is the process of using information about a scholar to quantify the likelihood that person wrote certain articles. ReCiter is an application that attempts to do exactly that. ReCiter uses institutionally-maintained identity data such as name of department and year of terminal degree to predict which articles a given scholar has authored. To compute the overall score for a given candidate article from PubMed (and, optionally, Scopus), ReCiter uses: up to 12 types of commonly available, identity data; whether other members of a cluster have been accepted or rejected by a user; and the average score of a cluster. In addition, ReCiter provides scoring and qualitative evidence supporting why particular articles are suggested. This context and confidence scoring allows curators to more accurately provide feedback on behalf of scholars. To help users to more efficiently curate publication lists, we used a support vector machine analysis to optimize the scoring of the ReCiter algorithm. In our analysis of a diverse test group of 500 scholars at an academic private medical center, ReCiter correctly predicted 98% of their publications in PubMed.

Highlights

Author name disambiguation is the process of inferring, often using clustering techniques, whether the same author who wrote one paper wrote another paper
Many software initiatives have been engineered for the purpose of disambiguating author names in Medline data, and a subset of these have code that is publicly available for use
We describe ReCiter [11], an open source, identity-driven authorship prediction algorithm

Summary

Introduction

Author name disambiguation is the process of inferring, often using clustering techniques, whether the same author who wrote one paper wrote another paper. Many software initiatives have been engineered for the purpose of disambiguating author names in Medline data, and a subset of these have code that is publicly available for use. Author disambiguation software can be divided into those that perform unsupervised and supervised approaches. Techniques for unsupervised approaches generally involve clustering-based algorithms. One paper [1] discusses a K-way spectral clustering approach using features such as co-author names, paper titles, and publication venue titles. Another [2] describes an agglomerative clustering algorithm approach with pairwise similarity to disambiguate author names for PubMed using features such as title, affiliation, journal, co-authors, etc. Significant progress has been made, with several systems having a claimed accuracy in excess of 97% [6, 7]

Objectives

Methods

Results

Conclusion