Brain, Digital, & Learning

 Open access, Peer Reviewed

Indexed in KCI

pISSN 2384-2474
eISSN 2586-7490

RESEARCH ARTICLE

Analysis of Research Trends in Online Discussion Using Topic Modeling

1Oryong Middle School
2Korea National University of Education

Correspondence to Sook-Ki Choi, agrement@knue.ac.kr

Brain, Digital, & Learning. Volume 11, Number 3, 431‒445, September 2021. https://doi.org/10.31216/BDL.20210028
Received on May 10, 2021, Revised on May 26, 2021, Accepted on May 26, 2021, Published on September 30, 2021.
Copyright © 2021 Institute of Brain·AI based Education, Korea National University of Education. This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

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 teachinglearning 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.
Keywords

Online discussion, topic modeling, research trends, LDA, time series analysis

Section