Hostname: page-component-848d4c4894-pftt2 Total loading time: 0 Render date: 2024-05-13T08:37:18.217Z Has data issue: false hasContentIssue false

514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021

Published online by Cambridge University Press:  19 April 2022

Rosalina Das
Affiliation:
University of Miami
Jessica Diaz
Affiliation:
University of Miami
Sheela Dominguez
Affiliation:
University of Miami
Barry Issenberg
Affiliation:
University of Miami
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

OBJECTIVES/GOALS: The goal of this project was to perform an exploratory analysis of the research themes of scientific publications from the Miami Clinical and Translational Science Institute using text mining techniques and using bibliometric characterization and network analysis to further assess research trends. METHODS/STUDY POPULATION: Publications were identified from the Web of Science database using Miami CTSI grant numbers as search criteria for the period 2013-2021 and KL2 scholar publications. Following data pre-processing, topic modeling was performed using the Latent Dirichlet Allocation algorithm and cluster analysis in the R programming language. The resulting themes will be further analyzed by employing a citation-based impact assessment approach to identify trends over time. Network analysis of publications will be performed using the VOSviewer package to visualize publication networks using citation and co-authorship relations within each major theme and their evolution over time. Findings will be evaluated for alignment with institutional research strategy. RESULTS/ANTICIPATED RESULTS: About 400 CTSI publications from 2013-2021 to date were used for analysis. Twenty topics and five major research themes were identified among the Miami CTSI publications – neuroscience, cancer, community and public health, metabolics, and HIV/infectious diseases. Top keywords within each topic were aligned with the most frequent author-assigned keywords for that topic. The CTSI research themes were also well-aligned with the institutional vision for research and focus areas. Trends using citations and networks for each research theme are currently being analyzed and results will be included in the overall findings post analysis. DISCUSSION/SIGNIFICANCE: Text mining was successfully used in identifying topics and research themes for clinical and translational research publications of the Miami CTSI, and in combination with bibliometric characterization, will be helpful in shaping CTSI strategy and alignment with the universitys research priorities.

Type
Workforce Development
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (https://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
© The Author(s), 2022. The Association for Clinical and Translational Science