A topic modeling analysis of Korea’s T&I research trends in the 2010s

Abstract

The present study aims to demonstrate the relevance of topic modeling as a new research tool for analyzing research trends in the T&I field. Until now, most efforts to this end have relied on manual classification based on pre-established typologies. This method is time- and labor-consuming, prone to subjective biases, and limited in describing a vast amount of research output. As a key component of text mining, topic modeling offers an efficient way of summarizing topic structure and trends over time in a collection of documents while being able to describe the entire system without having to rely on sampling. As a case study, the present paper applies the technique to analyzing a collection of abstracts from four Korean Language T&I journals for the 2010s decade (from 2010 to 2019). The analysis proves the technique to be highly successful in uncovering hidden topical structure and trends in the abstract corpus. The results are discussed along with implications of the technique for the T&I field.