Author Name Disambiguation in MEDLINE

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.

Fig. 1

Presence of affiliations, email addresses and full first names in MEDLINE records as a function of publication date. The affiliations have been included (when available) since ~1988, most often containing the affiliation of the first-listed author or corresponding author only. Email addresses, although rarely available, have been included in the affiliation field since ~1995. Full first names have been included (when available) since 2002. Note that some first names and emails were extracted from bibliographic sources other than MEDLINE (see Results).

Fig. 2

Histogram of name counts in MEDLINE.

Fig. 3

Histogram of pairwise probabilities averaged over the corpus of COS profile gold standards.

Fig. 4

Number of author-individual clusters per name as a function of the number of articles per name. Values shown are mean ± S.D.

Fig. 5

Proportion of author-individual clusters containing a single article (“singletons”), as a function of the number of articles per name. Values shown are mean ± S.D.

Fig. 6

Size distribution of author-individual clusters, as a function of the number of articles per cluster. The distribution is the same for rare, moderate and very common names. (There is a deviation from a true power law for authors with many articles, which probably reflects the fact that individuals have a finite lifespan so no one person can publish too many articles.)

Fig. 7

Logistic regression curves showing the splitting rate (y-axis) as a function of name frequency (x-axis) and the year of publication (color coded curves) within the self-citation gold standard dataset.

Fig. 8

Frequencies of the six most common names in MEDLINE over time. The dots correspond to the observed values, and the lines show fitted regression curves.