Vetle I. Torvik
Abstract
Background: We recently described “Author-ity,” a model for estimating the probability that two articles in MEDLINE, sharing the same author name, were written by the same individual. Features include shared title words, journal name, coauthors, medical subject headings, language, affiliations, and author name features (middle initial, suffix, and prevalence in MEDLINE). Here we test the hypothesis that the Author-ity model will suffice to disambiguate author names for the vast majority of articles in MEDLINE. Methods: Enhancements include: (a) incorporating first names and their variants, email addresses, and correlations between specific last names and affiliation words; (b) new methods of generating large unbiased training sets; (c) new methods for estimating the prior probability; (d) a weighted least squares algorithm for correcting transitivity violations; and (e) a maximum likelihood based agglomerative algorithm for computing clusters of articles that represent inferred author-individuals. Results: Pairwise comparisons were computed for all author names on all 15.3 million articles in MEDLINE (2006 baseline), that share last name and first initial, to create Author-ity 2006, a database that has each name on each article assigned to one of 6.7 million inferred author-individual clusters. Recall is estimated at ∼98.8%. Lumping (putting two different individuals into the same cluster) affects ∼0.5% of clusters, whereas splitting (assigning articles written by the same individual to >1 cluster) affects ∼2% of articles. Impact: The Author-ity model can be applied generally to other bibliographic databases. Author name disambiguation allows information retrieval and data integration to become person-centered, not just document-centered, setting the stage for new data mining and social network tools that will facilitate the analysis of scholarly publishing and collaboration behavior. Availability: The Author-ity 2006 database is available for nonprofit academic research, and can be freely queried via http://arrowsmith.psych.uic.edu.
- Bhattacharya, I. and Getoor, L. 2006. A latent Dirichlet model for unsupervised entity resolution. In Proceedings of the 6th SIAM Conference on Data Mining, J. Ghosh, D. Lambert, D. B. Skillicorn, and J. Srivastava Eds. SIAM, 47--58.Google Scholar
- Bhattacharya, I. and Getoor, L. 2007. Collective entity resolution in relational data. ACM Trans. Knowl. Discov. Data 1, 1--36. Google ScholarDigital Library
- Bilenko, M., Kamath, B., and Mooney, R. J. 2006. Adaptive blocking: Learning to scale up record linkage. In Proceedings of the IEEE Computer Society 6th International Conference on Data Mining. 87--96. Google ScholarDigital Library
- Culotta, A. and McCallum, A. 2006. Tractable learning and inference of high-order representations. In Proceedings of the ICML Workshop on Open Problems in Statistical Relational Learning. http://www.cs.umd.edu/projects/srl2006/proceedings.html.Google Scholar
- Culotta, A., Kanani, P., Hall, R., Wick, M., and McCallum, A. 2007. Author disambiguation using error-driven machine learning with a ranking loss function. In Proceedings of the 6th AAAI International Workshop on Information Integration on the Web.Google Scholar
- Dominguez, J. and Gonzalez-Lima, M. D. 2006. A primal-dual interior-point algorithm for quadratic programming. Numer. Algor. 42, 1--30.Google ScholarCross Ref
- Fisher, D. H. 1987. Knowledge acquisition via incremental conceptual clustering. Mach. Learn. 2, 139--172. Google ScholarDigital Library
- French, J. C., Powell, A., and Schulman, E. 2000. Using clustering strategies for creating authority files. J. Amer. Soc. Inform. Sci. Technol. 51, 774--786. Google ScholarDigital Library
- Galvez, C. and Moya-Anegón, F. 2007. Approximate personal name-matching through finite state graphs. J. Amer. Soc. Inform. Sci. Technol. 58, 1960--1976. Google ScholarDigital Library
- Garfield, E. 1969. British quest for uniqueness versus American egocentrism. Nature 223, 763.Google ScholarCross Ref
- Han, H., Zha, H., and Giles, C. L. 2005. Name disambiguation in author citations using a K-way spectral clustering method. In Proceedings of the 5th ACM/IEEE Joint Conference on Digital Libraries. M. Marlino, T. Sumner, and F. M. Shipman III Eds. ACM, 334--343. Google ScholarDigital Library
- Han, H., Giles, C. L., Zha, H., Li, C., and Tsioutsiouliklis, K. 2004. Two supervised learning approaches for name disambiguation in author citations. In Proceedings of the 4th ACM/IEEE Joint Conference on Digital Libraries, H. Chen, H. D. Wactlar, C.-C. Chen, E.-P. Lim, and M. G. Christel Eds. ACM, 296--305. Google ScholarDigital Library
- Herskovic, J. R., Tanaka, L. Y., Hersh, W., and Bernstam, E. V. 2007. A day in the life of PubMed: analysis of a typical day's query log. J. Amer. Med. Inform. Ass. 14, 212--220.Google ScholarCross Ref
- Holmes, D. I., Robertson, M., and Paez, R. 2001. Stephen Crane and the New-York Tribune: A case study in traditional and non-traditional authorship attribution. Comput. Human. 35, 315--331.Google ScholarCross Ref
- Huang, J., Ertekin, S., and Giles, C. L. 2006. Efficient name disambiguation for large-scale databases. In Proceedings of the 10th European Conference on Principles and Practice of Knowledge Discovery in Databases, J. Fürnkranz, T. Scheffer, and M. Spiliopoulou Eds. Springer-Verlag, 536--544. Google ScholarDigital Library
- Jaro, M. A. 1995. Probabilistic linkage of large public health data files. Statis. Med. 14, 491--498.Google ScholarCross Ref
- Kalashnikov, D. V. and Mehrotra, S. 2006. Domain-independent data cleaning via analysis of entity-relationship graph. ACM Trans. Data. Syst. 31, 716--767. Google ScholarDigital Library
- Kanani, P., McCallum, A., and Pal, C. 2007. Improving author coreference by resource-bounded information gathering from the Web. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, M. M. Veloso Ed. 429--434. Google ScholarDigital Library
- Koudas, N., Sarawagi, S., and Srivstava, D. 2006. Record linkage: Similarity measures and algorithms. In Proceedings of the ACM SIGMOD International Conference on Management of Data, 802--803. (Supplementary tutorial slides available from http://queens.db.toronto.edu/koudas/docs/aj.pdf.) Google ScholarDigital Library
- Madigan, D., Genkin, A., Lewis, D. D., Argamon, S., Fradkin, D., and Ye, L. 2005. Author identification on the large-scale. Annual Meeting of the Classification Society of North America. http://www.stat.rutgers.edu/~madigan/PAPERS/authorid-csna05.pdf.Google Scholar
- Mann, G. S. and Yarowsky, D. 2003. Unsupervised personal name disambiguation. In Proceedings of the 7th Conference on Natural Language Learning. Association for Computational Linguistics, Morristown, 33--40. Google ScholarDigital Library
- On, B. W., Lee, D., Kang, J., and Mitra, P. 2005. Comparative study of name disambiguation problem using a scalable blocking-based framework. In Proceedings of the 5th ACM/IEEE Joint Conference on Digital Libraries 2. M. Marlino, T. Sumner, F. M. Shipman III Eds. ACM, 344--353. Google ScholarDigital Library
- Qiu, J. 2008. Scientific publishing: identity crisis. Nature 451, 766--767.Google ScholarCross Ref
- Reuther, P. and Walter, B. 2006. Survey on test collections and techniques for personal name matching. Int. J. Metadata, Seman. Ontol. 1, 89--99. Google ScholarDigital Library
- Scoville, C. L., Johnson, E. D., and McConnell, A. L. 2003. When A. rose is not A. Rose: The vagaries of author searching. Med. Refer. Serv. Quart. 22, 1--11.Google ScholarCross Ref
- Smalheiser, N. R., Zhou, W., and Torvik, V. I. 2008. Anne O'Tate: A tool to support user-driven summarization, drill-down and browsing of PubMed search results. J. Biomed. Discov. Collab. 3, 2.Google ScholarCross Ref
- Smalheiser, N. R. and Torvik, V. I. 2009. Author name disambiguation. In Annual Review of Information Science and Technology 43, B. Cronin Ed. 287--313. Google ScholarDigital Library
- Smalheiser, N. R., Torvik, V. I., and Zhou, W. 2009. Arrowsmith two-node search interface: A tutorial on finding meaningful links between two disparate sets of articles in MEDLINE. Comput. Meth. Prog. Biomed. 94, 190--197. Google ScholarDigital Library
- Soler, J. M. 2007. Separating the articles of authors with the same name. Scientometrics 72, 281--290.Google ScholarCross Ref
- Song, Y., Huang, J., Councill, I. G., Li, J., and Giles, C. L. 2007. Efficient topic-based unsupervised name disambiguation. In Proceedings of the ACM/IEEE Joint Conference on Digital Libraries. E. M. Rasmussen, R. R. Larson, E. Toms, and S. Sugimoto Eds. ACM, 342--351. Google ScholarDigital Library
- Tan, Y. F., Kan, M. Y., and Lee, D. 2006. Search engine-driven author disambiguation. In Proceedings of the 6th ACM/IEEE Joint Conference on Digital Libraries. G. Marchionini, M. L. Nelson, and C. C. Marshall Eds. ACM, 314--315. Google ScholarDigital Library
- Torvik, V. I., Weeber, M., Swanson, D. R., and Smalheiser, N. R. 2005. A probabilistic similarity metric for Medline records: A model for author name disambiguation. J. Amer. Soc. Inform. Sci. Technol. 56, 140--158. Google ScholarDigital Library
- Torvik, V. I. and Smalheiser, N. R. 2007. A quantitative model for linking two disparate sets of articles in MEDLINE. Bioinformatics 23, 1658--1665. Google ScholarDigital Library
- Wilbur, W. J. and Yang, Y. 1996. An analysis of statistical term-strength and its use in the indexing and retrieval of molecular biology texts. Comput. Bio. Med. 26, 209--222.Google ScholarCross Ref
- Winkler, W. E. 1995. Matching and record linkage. In Business Survey Methods, B. G. Cox, D. A. Binder, B. N. Chinnappa, A. Christianson, M. J. Colledge, and P. S. Kott Eds. Wiley, New York, 355--384.Google Scholar
- Yin, X., Han, J., and Yu, P. S. 2007. Object distinction: Distinguishing objects with identical names by link analysis. In Proceedings of the IEEE 23rd International Conference on Data Engineering. IEEE, 1242--1246.Google Scholar
Index Terms
- Author name disambiguation in MEDLINE
Recommendations
Web personal name disambiguation based on reference entity tables mined from the web
WIDM '09: Proceedings of the eleventh international workshop on Web information and data managementAmbiguous personal names are common on the Web, which pose a challenge for many different tasks. The traditional disambiguation employs the clustering methods. However, without reference entity tables, the clustering method can only identify whether two ...
Name Disambiguation Using Semantic Association Clustering
ICEBE '09: Proceedings of the 2009 IEEE International Conference on e-Business EngineeringDue to homonyms, abbreviations, etc., name ambiguity is widely available in web and e-document. For example, when integrating heterogeneous literature databases, because there are different name specifications, different authors may be thought of as the ...
Name disambiguation in author citations using a K-way spectral clustering method
JCDL '05: Proceedings of the 5th ACM/IEEE-CS joint conference on Digital librariesAn author may have multiple names and multiple authors may share the same name simply due to name abbreviations, identical names, or name misspellings in publications or bibliographies 1. This can produce name ambiguity which can affect the performance ...
Reviews
Quinsulon Israel
Solving the difficult problem of author name disambiguation will help greatly with social networking analysis and determining an individual author's "image." Partitioning articles along multiple dimensions-such as name derivation, email address, coauthor identification, self-citations, and research areas-has shown that articles can be accurately identified as belonging to the correct person, even when the name of the individual on those separate articles is derived or incomplete. As a byproduct of this research area, the links between these partitions (individual authors) and the links between the works within these partitions can be studied for further conjectures about an author's collaborative research and relationships. Torvik and Smalheiser provide readers with a thorough understanding of the problem, the solutions, and the issues in between, including a clear presentation of their methodology. They use many methods that are becoming fundamental, such as similarity analysis of multidimensional vectors. However, although the paper is very well organized, it suffers greatly from conceptual overload, so that the many statistics and discoveries are lost in the dense text. The paper needs more adequate listings, tables, and diagrams to help readers better conceptualize the reported findings. The authors' ingenuity is apparent in their robust and valid dataset. The freely available dataset performs well against other author disambiguation resources. Unfortunately, the authors heavily cite their own work, with few references to other approaches and research. Despite the paper's weaknesses, I still recommend it to those who are interested in author name disambiguation; those who are looking for an excellent dataset; and those who are interested in similarity measures and experimenting with author metadata. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments