Heuristical Research on Twelve Decades of Information and Knowledge Creation Utilizing Python and NLP

Abstract

Publications on knowledge and information creation have grown significantly due to their importance in information and knowledge management. This study aims to discover and analyze the hidden thematic topics of information and knowledge creation publications. The research applied was performed using text mining techniques and an analytical approach. The research population comprises publications on knowledge and information creation from 1900 to 2021, retrieved from the Web of Science Core Collection (WOSCC). The data were analyzed by Latent Dirichlet Allocation (LDA) algorithm and Python Programming Language. Forty-eight thousand two hundred sixty-five documents were retrieved and analyzed. "Data production," "Health seeking behavior," "Human Brain and Information processing," "Decision-making models," "Knowledge production," "Information needs," and "Digital Literacy" are among the essential topics in order of publication rate. The results indicated that the spectrum of the fourteen topics covered a variety of dimensions, including "data and knowledge creation," "information processing," "information needs and behavior," "digital literacy," and "critical thinking." The study's findings have shown the conceptual relationships between textual data and the presentation of the knowledge structure of information and knowledge creation. Based on this, it can be concluded that the creation of knowledge and information includes human mental and behavioral processes concerning knowledge.

Keywords

• knowledge creation
• information creation
• data creation
• data mining
• text mining
• topic modeling
• latent dirichlet allocation (lda)