Three Kinds of Disambiguated Author ID Systems for PubMed 2019

Author identifier (ID) is essential for many downstream tasks, such as co-author network and scientist mobility analysis. As a widely used bibliometrics database, author ID of PubMed is not officially provided by National Institutes of Health (NIH), that restrict bibliometric research. This study exploited three open bibliographic databases Aminer, Microsoft Academic Graph (MAG) and Semantic Scholar (S2) to associate author ID for PubMed. For this purpose, paper linking and author linking was performed sequencely to mine paper and author links between PubMed and these databases. Performance of author name disambiguation (AND) of there available identifiers was evaluated on two AND datasets. Our findings suggested that, S2 contains full volume of PubMed regarding link completeness. With respect to correctness of author ID, S2 and MAG achieved better performance than Aminer. The best F1 score on both dataset of there available identifiers is below 90\%, indicate that AND for large scale database remain as a difficult task and the need for further improvement. We made the final dataset that contains linked paper and author of PubMed publicly available for facilitating future research.