Analysis of Research Data in Information Science Using the Topic Modeling Method

Abstract

Most research data in the modern world are in digital format, and there is therefore a need to develop high-efficiency tools that can provide access to and an understanding of these data. Computerization technology based on natural language processing with a capacity for topic extraction and categorization would enable us to identify new topics and future directions for research in several fields of study. The aim of this research was to analyze and categorize information science research data obtained from journals listed in an international database between 2013 and 2019. The research methodology applied here was data analysis based on the topic modeling method, a technique used to locate word groups or topics from a corpus containing complicated and difficult works. This method yields reliable and high-accuracy outcomes. The data analyzed here were drawn from research articles published in information science journals, the names of which were listed in the Scimago Journal and Country Rank between 2013 and 2019. Only journals in the Web of Science and articles written in English were included. A total of 30,571 research articles obtained from 677 volumes of 99 journals were analyzed using the topic modeling method, and topics were assigned by experts in the field. The findings revealed that over the past seven years, research was carried out on 30 topics in information science. The five most frequently researched topics were competency development, data management, social media analytics, public and community services, and bioinformatics. A comparison with other research data analyzed in the field of information science over the past five years using other techniques showed clear differences and a tendency of the research topics to change. The results of this research can greatly benefit the identification of research directions for the future.