Methodologically grounded semantic analysis of large volume of chilean medical literature data applied to the analysis of medical research funding efficiency in Chile

Abstract

Background Medical knowledge is accumulated in scientific research papers along time. In order to exploit this knowledge by automated systems, there is a growing interest in developing text mining methodologies to extract, structure, and analyze in the shortest time possible the knowledge encoded in the large volume of medical literature. In this paper, we use the Latent Dirichlet Allocation approach to analyze the correlation between funding efforts and actually published research results in order to provide the policy makers with a systematic and rigorous tool to assess the efficiency of funding programs in the medical area. Results We have tested our methodology in the Revista Médica de Chile, years 2012-2015. 50 relevant semantic topics were identified within 643 medical scientific research papers. Relationships between the identified semantic topics were uncovered using visualization methods. We have also been able to analyze the funding patterns of scientific research underlying these publications. We found that only 29% of the publications declare funding sources, and we identified five topic clusters that concentrate 86% of the declared funds. Conclusions Our methodology allows analyzing and interpreting the current state of medical research at a national level. The funding source analysis may be useful at the policy making level in order to assess the impact of actual funding policies, and to design new policies.

Cultural heritage through the lens of COVID-19

“…In order to perform topic modeling on the translated Instagram posts, we used (LDA), the most widely used topic modeling algorithm ( Kapoor et al, 2018 ; Wolff et al, 2020 ). To estimate the optimal quantity of topics, we applied the ldatuning package ( Nikita & Chaney, 2016 ) which calculates four different metrics relative to the document-term matrix of the Instagram posts corpus in order to identify a preferable number of topics for the LDA model.…”

“…In the two-dimensional space, the distance between the circles’ centers is a measure of the similarity of the topics: the most closely related topics have the shortest distance. This method allows topics to overlap each other in terms of content, rather than being separated into discrete groups, in a way that mirrors the typical use of natural language ( Wolff et al, 2020 ). This tool allows us to grasp the meaning of each topic, to determine the prevalence of each topic in the Instagram posts, and to infer the similarity link between each of the obtained topics.…”