|
KMID : 1002520170110040213
|
|
Korean Journal of Health Service Management
2017 Volume.11 No. 4 p.213 ~ p.224
|
|
|
Analysis on Topic Trends and Topic Modeling of KSHSM Journal Papers using Text Mining
|
|
Cho Kyoung-Won
Bae Sung-Kwon
Woo Young-Woon
|
|
|
Abstract
|
|
|
Objectives : The purpose of this study was to analyze representative topics and topic trends of papers in Korean Society and Health Service Management(KSHSM) Journal.
Methods : We collected English abstracts and key words of 516 papers in KSHSM Journal from 2007 to 2017. We utilized Python web scraping programs for collecting the papers from Korea Citation Index web site, and RStudio software for topic analysis based on latent Dirichlet allocation algorithm.
Results : 9 topics were decided as the best number of topics by perplexity analysis and the resultant 9 topics for all the papers were extracted using Gibbs sampling method. We could refine 9 topics to 5 topics by deep consideration of meanings of each topics and analysis of intertopic distance map. In topic trends analysis from 2007 to 2017, we could verify ‘Health Management’ and ‘Hospital Service’ were two representative topics, and ‘Hospital Service’ was prevalent topic by 2011, but the ratio of the two topics became to be similar from 2012.
Conclusions : We discovered 5 topics were the best number of topics and the topic trends reflected the main issues of KSHSM Journal, such as name revision of the society in 2012.
|
|
|
KEYWORD
|
|
|
LDA, Text Mining, Topic Modeling, KSHSM Journal, LDA
|
|
|
FullTexts / Linksout information
|
|
|
|
|
|
Listed journal information
|
|
|