Topic Analysis of Published Articles in Medical librarianship and Information Science in Iran Using Text Mining Techniques

Background and Objectives: Nowadays, due to the increasing publication of articles in various scientific fields, analysis of the topics published in specialized journals is interesting for researchers and practioners. For this purpose, this study has identified and analyzed the issues published in the Iranian library and medical librarianship articles.
Material and Method: This study uses an exploratory and descriptive approach to analyze the library and information articles published in specialized journals in this field in Iran from 1997 to 2017 using text mining techniques. For this purpose, 982 articles on the library and medical librarianship have been selected from 16 journals. The TF-IDF weighting algorithm was used to identify the most important terms used in the articles and the LDA thematic modeling algorithm was used to determine the published topics. Python programming language has also been used to run text mining algorithms.
Results: Results showed that the words of library (12.67), journal (12.47), information (12.23), hospital (9.90) and scientific (9.74) are the most important words based on their TF-IDF weight. The results of thematic modeling of these articles were based on the highest publication rates of scientometrics, information literacy, health information, knowledge management, webometrics, and the quality of the website and hospital information systems, respectively.
Conclusion: The results of this study showed that the topics of scientometrics, information literacy and health information have had the highest publication in the last 5 years. Also, the publication of knowledge management, webometrics and quality of the website and hospital information system has been less published in the last 5 years than in the past.