Three Journal Similarity Metrics and Their Application to Biomedical Journals

Abstract

In the present paper, we have created several novel journal similarity metrics. The MeSH odds ratio measures the topical similarity of any pair of journals, based on the major MeSH headings assigned to articles in MEDLINE. The second metric employed the 2009 Author-ity author name disambiguation dataset as a gold standard for estimating the author odds ratio. This gives a straightforward, intuitive answer to the question: Given two articles in PubMed that share the same author name (lastname, first initial), how does knowing only the identity of the journals (in which the articles were published) predict the relative likelihood that they are written by the same person vs. different persons? The article pair odds ratio detects the tendency of authors to publish repeatedly in the same journal, as well as in specific pairs of journals. The metrics can be applied not only to estimate the similarity of a pair of journals, but to provide novel profiles of individual journals as well. For example, for each journal, one can define the MeSH cloud as the number of other journals that are topically more similar to it than expected by chance, and the author cloud as the number of other journals that share more authors than expected by chance. These metrics for journal pairs and individual journals have been provided in the form of public datasets that can be readily studied and utilized by others.

Two Similarity Metrics for Medical Subject Headings (MeSH): An Aid to Biomedical Text Mining and Author Name Disambiguation

“…Finally, we calculated the MeSH odds ratio for each pair of MeSH terms present in that bin, by taking the observed co-occurrence score divided by the average co-occurrence score for that bin. This is similar to the manner in which odds ratios were computed for journal similarity metrics in D’Souza and Smalheiser (2014) . (Note the author-based metric described in the present paper relates any two MeSH terms according to how likely they are to appear in the articles written by the same author.…”

“…For each article included in the 2014 baseline version of MEDLINE, we extracted the Medical Subject Headings (MeSH) indexed in the MEDLINE record, and calculated the number of times that each pair of MeSH terms co-occurred within the same article, as well as the total number of articles in which each MeSH term occurred. A stoplist of the 20 most frequent MeSH terms ( D’Souza and Smalheiser, 2014 ) was employed to remove them from consideration, since highly frequent terms would appear to be similar to all other MeSH terms. Only those MeSH terms appearing in at least 25 articles were considered in calculating term similarity measures and odds ratios, since lower values would be highly subject to noise.…”

Two Similarity Metrics for Medical Subject Headings (MeSH): An Aid to Biomedical Text Mining and Author Name Disambiguation

“…For example, two journals may cover the same topic (e.g., Scandinavian Journal of Immunology vs. Iranian Journal of Immunology), yet the same person may have very little likelihood of publishing articles in both journals. Thus, the 2009 Author-ity disambiguation dataset was earlier mined to create a metric that comprehensively measures the tendency of individuals to publish articles in any two journals (D'Souza and Smalheiser, 2014). Here, the author metric measures the tendency of individuals to publish a body of articles that is indexed by any two different MeSH terms during their careers.…”

Using latent semantic analysis for automated keyword extraction from large document corpora

“…Eqs. (6) and 7depict the formulas for each N percent increment of FPR on the x-axis and TPR on the y-axis.…”

“…MeSH vocabulary is used as keywords in some keyword extraction studies [5]. Based on the MeSH terms, the topical similarity of biomedical documents can be computed [6]. MeSH terms are assigned manually by human curators to each PubMed article using a controlled, hierarchical vocabulary.…”