back
Further research project
Innovation and Entrepreneurship Research

sosia

Econometric analysis in Economics of Science and Innovation often requires the identification of a control group with similar observable characteristics to a sample of researchers of interest. The established standard is to apply matching methodologies on a larger population of researchers with information mostly manually constructed. This may constitute a daunting data effort and a impracticable option for samples crossing multiple fields. At the same time, name ambiguity and truncation of historical data prevent the blind use of the bibliographic databases available to be purchased and processed offline. sosia is a Python-based software designed to query efficiently and automatically the Scopus on-line database via RESTful API, in search for researchers with publication profiles similar to a given researcher up to a given year. It considers standard indicators derived from bibliographic information. The user can choose flexibly a set of parameters to restrict upfront the search to more or less narrow boundaries or obtain additional similarity indicators to select a subset of authors after the search.

Fields of Research