Analysis of Research Trends in Online Discussion Using Topic Modeling

• 영문명: 토픽 모델링 분석을 활용한 온라인 토론에 관한 연구 경향 분석
• 발행기관: 한국교원대학교 뇌기반교육연구소
• 저자명: 김세화(Se-Hwa Kim) 최숙기(Sook-Ki Choi)
• 간행물 정보: 『Brain, Digital, & Learning』제11권 제3호, 431~445쪽, 전체 15쪽
• 주제분류: 사회과학 > 교육학
• 파일형태: PDF
• 발행일자: 2021.09.30

영문 초록

Online discussion is a major form of discourse in modern society and a teaching-learning method that is important in an online learning environment. The purpose of this study is to explore the research direction by considering the research on online discussion. The subjects of the analysis are the title, keywords, and abstracts of Academic papers from 2011 to 2020. After conducting textual analysis, conduct LDA-based topic modeling with Gibbs sampling and conduct time series analysis for analysis of research trends over the years. Seven topics were extracted through topic modeling. These are classified into two aspects, respectively: online discussion as teaching-learning methods and online discussion as online discourse forming methods. Among them, research on aspects of online discussion as teachingꠓlearning methods in online class settings has been addressed as a relatively more important topic. According to the annual time series analysis, the research topic on online discussion as teaching-learning activity decreased, but after COVID-19, remote classes began to be introduced in earnest, and it began to increase rapidly again. On the one hand, research related to dashboard and visualization analysis for learner interaction analysis has shown a steady increase. Topics on online discussion as an act of social participation or political communication have emerged as a cold topic, while topics on discourse analysis in online communities of members of society based on online discussion have emerged as a hot topic. Based on these findings, We discussed the direction of follow-up research for the continuous and significant development of online discussion.

목차

Introduction

Background

Method

Results

Conclusions

키워드

Online discussion topic modeling research trends LDA time series analysis