Cargando…
514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021
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...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Cambridge University Press
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9209179/ http://dx.doi.org/10.1017/cts.2022.308 |
_version_ | 1784729888635224064 |
---|---|
author | Das, Rosalina Diaz, Jessica Dominguez, Sheela Issenberg, Barry |
author_facet | Das, Rosalina Diaz, Jessica Dominguez, Sheela Issenberg, Barry |
author_sort | Das, Rosalina |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-9209179 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Cambridge University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-92091792022-07-01 514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021 Das, Rosalina Diaz, Jessica Dominguez, Sheela Issenberg, Barry J Clin Transl Sci Workforce Development 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. Cambridge University Press 2022-04-19 /pmc/articles/PMC9209179/ http://dx.doi.org/10.1017/cts.2022.308 Text en © The Association for Clinical and Translational Science 2022 https://creativecommons.org/licenses/by-nc-nd/4.0/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. |
spellingShingle | Workforce Development Das, Rosalina Diaz, Jessica Dominguez, Sheela Issenberg, Barry 514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021 |
title | 514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021 |
title_full | 514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021 |
title_fullStr | 514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021 |
title_full_unstemmed | 514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021 |
title_short | 514 Using text mining approaches to identify research trends – an exploratory analysis of Miami Clinical and Translational Science Institute publications from 2013-2021 |
title_sort | 514 using text mining approaches to identify research trends – an exploratory analysis of miami clinical and translational science institute publications from 2013-2021 |
topic | Workforce Development |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9209179/ http://dx.doi.org/10.1017/cts.2022.308 |
work_keys_str_mv | AT dasrosalina 514usingtextminingapproachestoidentifyresearchtrendsanexploratoryanalysisofmiamiclinicalandtranslationalscienceinstitutepublicationsfrom20132021 AT diazjessica 514usingtextminingapproachestoidentifyresearchtrendsanexploratoryanalysisofmiamiclinicalandtranslationalscienceinstitutepublicationsfrom20132021 AT dominguezsheela 514usingtextminingapproachestoidentifyresearchtrendsanexploratoryanalysisofmiamiclinicalandtranslationalscienceinstitutepublicationsfrom20132021 AT issenbergbarry 514usingtextminingapproachestoidentifyresearchtrendsanexploratoryanalysisofmiamiclinicalandtranslationalscienceinstitutepublicationsfrom20132021 |