Search

Showing total 3 results
3 results

1. Analysis of Persian Bioinformatics Research with Topic Modeling.

Author

Ebrahimi, Fezzeh, Dehghani, Mohammad, and Makkizadeh, Fatemah

Subjects
LIFE sciences, RESEARCH, BIOMARKERS, PHONOLOGICAL awareness, MATHEMATICAL models, NATURAL language processing, RESEARCH methodology, BIBLIOMETRICS, MOLECULAR models, BIOINFORMATICS, MATHEMATICS, CITATION analysis, GENE expression, THEORY, MEDICAL research, INFORMATION technology, ALGORITHMS
Abstract

Purpose. As a scientific field, bioinformatics has drawn remarkable attention from various fields, such as information technology, mathematics, and modern biological sciences, in recent years. The topic models originating from the field of natural language processing have become the focus of attention with the rapid accumulation of biological datasets. Thus, this research is aimed at modeling the topic content of the bioinformatics literature presented by Iranian researchers in the Scopus Citation Database. Methodology. This research was a descriptive-exploratory study, and the studied population included 3899 papers indexed in the Scopus database, which had been indexed in this database until March 9, 2022. The topic modeling was then performed on the abstracts and titles of the papers. A combination of LDA and TF-IDF was utilized for topic modeling. Findings. The data analysis with topic modeling resulted in identifying seven main topics "Molecular Modeling," "Gene Expression," "Biomarker," "Coronavirus," "Immunoinformatics," "Cancer Bioinformatics," and "Systems Biology." Moreover, "Systems Biology" and "Coronavirus" had the largest and smallest clusters, respectively. Conclusion. The present investigation demonstrated an acceptable performance for the LDA algorithm in classifying the topics included in this field. The extracted topic clusters indicated excellent consistency and topic connection with each other. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

2. Subject-Related Research Metrics in Different Scientometrics Platforms.

Author

Khorasani, Mahyar

Subjects
DATABASES, COMPUTER software, MEDICAL information storage & retrieval systems, ACCOUNTING, BIBLIOMETRICS, SERIAL publications, QUANTITATIVE research, PSYCHOLOGY, CITATION analysis, MATHEMATICS, ECONOMICS, HUMANITIES, SCIENCE, AUTHORSHIP, ALGORITHMS
Abstract

This article investigates subject-related research metrics from the most popular scientometrics platforms with the capability of citation count. Quantitative analyses have been carried out to determine the most- to the least-cited subject areas to indicate the most active and dynamic fields in research. Subject areas are classified based on statistical analyses and the number of citations received in the period of search. Numerous articles were analyzed from top-ranked journals in all research fields covered by SCImago journal classification. A comprehensive data set was generated in 27 research subject areas, including 313 subject categories and 81 high-ranked journals. Results showed that the highest number of citations were related to the sciences and science-related subject areas. The subject areas of computer science and mathematics had the lowest research metrics and the smallest number of highly cited publications. Web of Science performed better than Scopus for subject-related evaluations. Analysis of frequency data showed that Google Scholar cited fewer papers for low-cited publications than did Scopus or Web of Science. For highly cited publications, however, Google Scholar was found to have better performance. Web of Science showed the best consistency in citation coverage in most of the investigated subject areas. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

3. Can co-authorship networks be used to predict author research impact? A machine-learning based analysis within the field of degenerative cervical myelopathy research

Author

Noah Grodzinski, Benjamin Davies, Ben Grodzinski, Grodzinski, Ben [0000-0001-8839-4718], and Apollo - University of Cambridge Repository

Subjects
FOS: Computer and information sciences, Biomedical Research, Social connectedness, Computer science, International Cooperation, Field (computer science), Machine Learning, Mathematical and Statistical Techniques, Knowledge extraction, Japan, Medical Laboratory Personnel, Musculoskeletal System, Multidisciplinary, Computer and information sciences, Artificial neural network, Applied Mathematics, Simulation and Modeling, Statistics, Opinion leadership, Neurodegenerative Diseases, Research Assessment, Research Personnel, Physical sciences, Medicine, Anatomy, Network Analysis, Algorithms, Network analysis, Research Article, Neural Networks, Science, FOS: Physical sciences, Bibliometrics, Spinal Cord Diseases, Machine Learning Algorithms, Artificial Intelligence, Humans, Statistical Methods, Set (psychology), Skeleton, Artificial Neural Networks, Retrospective Studies, Computational Neuroscience, Medicine and health sciences, Biology and life sciences, Computational Biology, Data science, Spine, Authorship, Research and analysis methods, North America, Neural Networks, Computer, Mathematics, Neck, Neuroscience, Forecasting
Abstract

Introduction Degenerative Cervical Myelopathy (DCM) is a common and disabling condition, with a relatively modest research capacity. In order to accelerate knowledge discovery, the AO Spine RECODE-DCM project has recently established the top priorities for DCM research. Uptake of these priorities within the research community will require their effective dissemination, which can be supported by identifying key opinion leaders (KOLs). In this paper, we aim to identify KOLs using artificial intelligence. We produce and explore a DCM co-authorship network, to characterise researchers’ impact within the research field. Methods Through a bibliometric analysis of 1674 scientific papers in the DCM field, a co-authorship network was created. For each author, statistics about their connections to the co-authorship network (and so the nature of their collaboration) were generated. Using these connectedness statistics, a neural network was used to predict H-Index for each author (as a proxy for research impact). The neural network was retrospectively validated on an unseen author set. Results DCM research is regionally clustered, with strong collaboration across some international borders (e.g., North America) but not others (e.g., Western Europe). In retrospective validation, the neural network achieves a correlation coefficient of 0.86 (p Discussion Analysis of the neural network shows that the nature of collaboration strongly impacts an author’s research visibility, and therefore suitability as a KOL. This also suggests greater collaboration within the DCM field could help to improve both individual research visibility and global synergy.

Published
2021