Topic Modeling on System Thinking Themes Using Latent Dirichlet Allocation, Non-Negative Matrix Factorization and BER Topic

In recent years, there has been a growing interest in Systems Thinking (ST) as a significant area of research. It has become increasingly crucial to provide a detailed overview of the ST domain and to identify the prevailing research focuses and trends within this realm. This study represents the most comprehensive and pioneering effort, using topic modeling analysis to analyze the landscape of ST research from the past to the present. The primary objective of this study was to identify the current state of research and the predominant areas of focus within articles related to ST. To achieve this research aim, a search was conducted on August 20, 2023, using the Scopus database, yielding 1400 articles. The bibliometric analysis findings of this study indicate a substantial surge in the number of publications in this field, especially since 2016, with a significant majority of these studies originating from the United States. While the research is characterized by its interdisciplinary nature, most publications fall within social science. Employing Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), and Bidirectional Encoder Representations (BER) Topic algorithms for topic modeling analysis, the study classified the articles into ten distinct topics. These topics encompass "comprehending and modeling complex systems," "sustainability in business," "interdisciplinary learning and problem-solving in education," "enhancing healthcare delivery," "system dynamics modeling," "engineering education," "chemistry education," "enhancing patient outcomes," "environmental sustainability," and "improving organizational performance."  The most prominent topics that represent common research areas in the field of Systems Thinking include "system dynamics modeling," "enhancing healthcare delivery," "interdisciplinary learning and problem-solving in education," "comprehending and modeling complex systems," "environmental sustainability," and "improving organizational performance". In conclusion, this study is expected to provide valuable guidance for future research in the field of Systems Thinking by aiding in identifying research interests and trends.