Analysis of Persian Bioinformatics Research with Topic Modeling.

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.

ParsBERT topic modeling of Persian scientific articles about COVID-19.

Purpose: The COVID-19 pandemic has indisputably impacted every aspect of human life, and a host of studies have investigated its different aspects. This paper models the contents of Persian literature on COVID-19. Method: This is a descriptive-exploratory study in which 815 articles were collected from the Magiran database. The articles were published before March 2022. The abstracts and titles were used in the modeling. The modeling was performed by combining the latent Dirichlet allocation (LDA) algorithm with ParsBERT. Findings: Topic modeling indicated ten major topics, including medicine, psychology, humanities, politics, management, biology, economics, culture, engineering, and religion. The articles under the category of medicine had the largest cluster (42.3%), while engineering and religion had the smallest clusters (1.1% each). Conclusion: The found topics in the created clusters have structural relationships. The COVID-19 effect on physical and mental health (medical and psychological topics) is the most crucial factor. These clusters provide evidence that COVID-19 affects all facets of human society at three levels: the individual, family, and society. Aside from the ten critical clusters in the humanities field, the utmost disorder is related to teaching and learning. For the first time, this research has presented a model of scientific communication in the field of COVID-19 based on the data collected from a Persian database - Magiran.

Theme trends and knowledge structure on health communication: Bibliometric analysis in PubMed database

Health communication is a new field focusing on the “powerful role” of human and media communication in health care services and health promotion. This study intends to explore the intellectual structure of knowledge in health communication literature using the co-word analysis technique. The applied descriptive-analytical method was used in this study to analyze the literature content with a hierarchical clustering approach. For data collection, the descriptors of the keyword “Health Communication” were searched in the medical subject heading (MeSH) in the PubMed database on November 18, 2021, for the period of 1959–2021. Data analysis and clustering were performed using SPSS software (version 20), RavarPremap software, Excell, Ucinet and VosViewer software. Data analysis indicates that scientific articles on communication health have experienced ascending growth pattern. Moreover, the findings on hierarchical clustering led to the formation of six subject clusters with the predominant subjects of " COVID-19 Pandemic, Health Education & Vaccine Hesitancy." The present study revealed a structural relationship among subject concepts in the clusters created with common features within each group. This study provided valuable insights into scientific communication patterns in health communication research produced in the PubMed database.