CIRSS Seminar: Shubhanshu Mishra

Doctoral student Shubhanshu Mishra will present, "Quantifying conceptual novelty in the biomedical literature."

Abstract: We introduce several measures of novelty for a scientific article in MEDLINE based on the temporal profiles of its assigned Medical Subject Headings (MeSH). First, temporal profiles for all MeSH term (and pairs of MeSH terms) were characterized empirically and modelled as logistic growth curves. Second, a paper's novelty is captured by its youngest MeSH (and pairs of MeSH) as measured in years and volume of prior work. Across all papers in MEDLINE published since 1985, we find that individual concept novelty is rare (2.7% of papers have a MeSH <= 3 years old; 1.0% have a MeSH <= 20 papers old), while combinatorial novelty is the norm (68% have a pair of MeSH <=3 years old; 90% have a pair of MeSH <= 10 papers old). Furthermore, these novelty measures exhibit complex correlations with article impact (as measured by citations received) and authors' professional age that have changed over time. All data and an interactive tool is available from http://abel.lis.illinois.edu/.

Bio: Shubhanshu Mishra is a third-year doctoral student at the iSchool at Illinois. He works as a research assistant with Assistant Professor Jana Diesner and Assistant Professor Vetle Torvik. His research involves using large scale data mining and machine learning solutions, to study the temporal evolution of science. His ongoing research work is focused on studying topical novelty of scientific articles, measuring relative topical expertise of authors on an article, and studying factors which affect the self-citation practices by authors. He recieved an integrated bachelor's and master's degree in mathematics and computing from the Indian Institute of Technology, Kharagpur in 2012. He was a fellow of Kishor Vaigyanik Protsahan Yojana (KVPY), a scholarship program funded by the Department of Science and Technology of the Government of India, from 2007 to 2012. More information on his projects can be found at http://shubhanshu.com/.