Browse School of Information Sciences by Author "Torvik, Vetle I."

  • Torvik, Vetle I.; Agarwal, Sneha (2016-03)
    We present a nearest neighbor approach to ethnicity classification. Given an author name, all of its instances (or the most similar ones) in PubMed are identified and coupled with their respective country of affiliation, ...

    application/pdf

    application/pdfPDF (38kB)
  • Mishra, Shubhanshu; Fegley, Brent D.; Diesner, Jana; Torvik, Vetle I. (2018-11-10)
    Authors contribute a wide variety of intellectual efforts to a research paper, ranging from initial conceptualization to final analysis and reporting, and many journals today publish the allocated responsibilities and ...

    application/pdf

    application/pdfPDF (184kB)
  • Torvik, Vetle I. (2015)
    Bibliographic records often contain author affiliations as free-form text strings. Ideally one would be able to automatically identify all affiliations referring to any particular country or city such as Saint Petersburg, ...

    application/pdf

    application/pdfPDF (589kB)
  • Mishra, Shubhanshu; Torvik, Vetle I. (2014-03-14)
    This research work is aimed at identifying novel topics and ideas in a given PubMed record. It will identify topics and ideas using which MeSH terms and MeSH pairs, respectively for a given PubMed record are novel, hot and ...

    application/pdf

    application/pdfPDF (1MB)
  • Mishra, Shubhanshu; Torvik, Vetle I. (2016-03-22)
    We introduce several measures of novelty for a scientific article in MEDLINE based on the concepts associated with it. The concepts associated with an article are identified using the Medical Subject Headings (MeSH) assigned ...

    application/pdf

    application/pdfPDF (248kB)
  • Agarwal, Sneha; Lincoln, Miles; Cai, Haoyan; Torvik, Vetle I. (GSLIS Research Showcase, 2014-03-14)
    Scientific research increasingly drives innovation and development of new technologies, and patent-to-paper citations can be used to trace this diffusion of knowledge and measure these science-to-technology spillover effects ...

    application/pdf

    application/pdfPDF (445kB)
  • Kehoe, Adam K.; Torvik, Vetle I. (ACM, 2016-06)
    We describe a classifier-enhanced nearest neighbor approach to assigning Medical Subject Headings (MeSH) to unlabeled documents using a combination of abstract similarities and direct citations to labeled MEDLINE records. ...

    application/pdf

    application/pdfPDF (303kB)
  • Mishra, Shubhanshu; Torvik, Vetle I. (2016-06-23)
    We present several measures and methods for quantifying conceptual novelty of an article in the biomedical literature corpus using a collection of 22 million MEDLINE articles. Our results show the prevalence of combinatorial ...

    application/pdf

    application/pdfPDF (2MB)
  • Torvik, Vetle I.; Cruz, Laura G. (2015-10)
    Models of human disease have traditionally been biased towards the male body. Here, we perform a retrospective study of factors that may have contributed to (reducing) this bias across a variety of biomedical topics and ...

    application/pdf

    application/pdfPDF (262kB)