Identification of Hot Topics and Trends in Knowledge and Information Science, Based on Text Mining Techniques

Identification of hot topics in research areas has always been of interest. Making smart decisions about what is needed to be studied is always a fundamental factor for researchers and can be challenging for them. The goal of this study is to identify hot topics and thematic trend analysis of articles indexed in Scopus database in the field of Knowledge and Information Science (KIS), between 2010 and 2019, by Text Mining techniques. The population consists of 50995 articles published in 249 journals indexed in Scopus database in the field of KIS from 2010 to 2019. To identify thematic clusters, algorithms of Latent Dirichlet Allocation (LDA) technique were used and the data were analyzed using libraries in Python software. To do this, by implementing the word weighting algorithm, using the TF-IDF method, and weighting all of the words and forming a text matrix, the topics in the documents and the coefficients for assigning each document to each topic (Theta) were determined. The output of the LDA algorithm led to the identification of the optimal number of 260 topics. Each topic was labeled based on the words with the highest weight assigned to each topic and with considering of experts’ opinions. Then, Topic clustering, keywords and topics identification were done. By performing calculations with 95% confidence, 63 topics were selected from 260 main topics. By calculating the average theta in years, 24 topics with a positive trend or slope (hot topic) and 39 topics with a negative trend or negative slope (cold topic) were determined. According to the results, measurement studies, e-management/ e-marketing, content retrieval, data analysis and e-skills, are considered as hot topics and training, archive, knowledge management, organization and librarians' health, were identified as cold topics in the field of KIS, in the period 2010 to 2019. The analysis of the findings shows that due to the interest of the most researchers in the last 10 years in using of emerging technologies, technology-based topics have attracted them more. In contrast, basic issues are less considered to be developed.