Topic analysis for the fourth industrial revolution using LDA and centrality analysis in Korea

Kyoung Ae Jang, Misun Park, Woo Je Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

The fourth industrial revolution is a recent hot issue in Korea. The purpose of this paper is to search the internet news related to the fourth industrial revolution and conduct topic analysis in order to fin. The idea and direction of the fourth industrial revolution in business, government, and industry. To this end, this study first collected internet news related the fourth industrial revolution in 2018. Second, the collected data were preprocessed to remove stop-words. Third, LDA analysis was performed with the refined data. As a result of LDA analysis, the keywords related to the fourth industrial revolution were classified into four categories. We found the main topics as Policy, New Technology, Industry and Finance. Fourth, word2vec analysis and centrality analysis were performed in order to analyze topics in detail. By analyzing centrality, it was able to derive to hidden topics which were not derived by LDA analysis. In addition, the intensity of the topic could be obtained through centrality analysis. As a result of centrality analysis, AI, Block Chain, Nation, Robot and Virtual Currency were elicited as new main topics. This study reveals concepts and directions of the fourth industrial revolution and can help guide relevant future policy for the fourth industrial revolution.

Original languageEnglish
Title of host publicationProceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018
EditorsDaniel Howard, Md Rezaul Bashar, Phill Kyu Rhee
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages108-116
Number of pages9
ISBN (Electronic)9781728104041
DOIs
StatePublished - 15 Jan 2019
Event2018 International Conference on Machine Learning and Data Engineering, iCMLDE 2018 - Sydney, Australia
Duration: 3 Dec 20187 Dec 2018

Publication series

NameProceedings - International Conference on Machine Learning and Data Engineering, iCMLDE 2018

Conference

Conference2018 International Conference on Machine Learning and Data Engineering, iCMLDE 2018
Country/TerritoryAustralia
CitySydney
Period3/12/187/12/18

Keywords

  • Centrality analysis
  • Latent Dirichlet Allocation analysis
  • The fourth industrial revolution
  • Topic modelling
  • Word2Vec analysis

Fingerprint

Dive into the research topics of 'Topic analysis for the fourth industrial revolution using LDA and centrality analysis in Korea'. Together they form a unique fingerprint.

Cite this