A method for clustering scientific publications based on natural language for the purpose of strategic planning of partnerships in interdisciplinary research

2024

Closed access Metadata (CSL-JSON)
DOI 10.1109/sist61555.2024.10629492
Data confidence 85 high
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The current research aims at examining the Kazakhstani scholars’ publications in order to reveal the topdiscussed topics and possible cooperation topics. By employing natural language processing, the research abstracts are grouped thematically to demonstrate the various clusters of themes present. The results reveal specific themes of the Kazakhstani research to provide the recommendations for the future academic development of the country and the cooperation between various fields. Thus, the approach illustrated the benefit of using thematic clustering for analysis and categorization of a vast amount of scholarly production.