Resolving Author Name Homonymy to Improve Resolution of Structures in Co-author Networks

TL;DR

This paper presents a scalable algorithm to resolve author name homonymy, improving the accuracy of co-author network structures by distinguishing node roles and assessing network distortion without extensive ground truth data.

Contribution

The authors introduce a novel, effective method for disambiguating author names in large co-author networks, enhancing the resolution of mesoscopic structures.

Findings

Algorithm effectively reduces network distortion caused by homonymy

Node role distinction improves network analysis accuracy

Method does not require extensive ground truth sampling

Abstract

We investigate how author name homonymy distorts clustered large-scale co-author networks, and present a simple, effective, scalable and generalizable algorithm to ameliorate such distortions. We evaluate the performance of the algorithm to improve the resolution of mesoscopic network structures. To this end, we establish the ground truth for a sample of author names that is statistically representative of different types of nodes in the co-author network, distinguished by their role for the connectivity of the network. We finally observe that this distinction of node roles based on the mesoscopic structure of the network, in combination with a quantification of author name commonality, suggests a new approach to assess network distortion by homonymy and to analyze the reduction of distortion in the network after disambiguation, without requiring ground truth sampling.