Quantifying the impact of funded research works

Abstract

A number of scientific publications discuss works that have been financially supported by agencies that invest in research. We refer to those publications as funded research works. In this paper, we try to capture the impact of funded research works, in order to assist funding agencies evaluate their efficacy in identifying the best research efforts. To accomplish our goal, we firstly need a method that automatically identifies publications that correspond to funded research. Our proposed method leverages NLP techniques in order to identify acknowledgments of financial support in the publications' content. Publications containing acknowledgments of financial support are deemed as funded works. Following the identification of funded research articles, we quantify their impact by considering the number of their citations, their freshness as well as the impact of their publication venue. The application of our method to a number of publications reveals that although funded research articles account to nearly 23% of the scientific publications, their average impact is increased compared to the average impact of non-funded publications. Our findings suggest that investments made on research deliver significant results and that funding agencies are effective in judging the potential impact of research efforts.