A Method of Modeling of Basic Big Data Analysis for Korean Medical Tourism: A Machine Learning Approach Using Apriori Algorithm

Abstract

Abstract. The Republic of Korea (ROK) has emerged as a country of superior medical tourism in the last decade among the people of China, Japan, Southeast Asia, Russia and the Middle East for the plastic surgery or others requiring precision skills. Although the ROK's medical tourism industry grew quantitatively in its revenue and the number of visitors, the report from the 2015 World Economic Forum concerning the competitiveness of ROK's tourism including the medical tourism showed that its rank had dropped to 29th position, a drop of 4 places from 25th in 2013. Thus, it is about time to improve the situation by investigating the actual conditions of tours taken by the foreign tourists to establish new strategy, which is the main contribution of this research. As a research method, a big data analysis has been performed on the basis of machine learning and using R-studio. During the analysis process, there were some relevant regularities which were difficult to be found in the big data and based on these findings, we have attempted to find the solutions for the bad images that foreign visitors had shared in common. The result of the big data analysis showed that the their purpose of visit was different from each other depending on the age groups and the details of their experience of inconvenience varied as well.

Golden years, golden shores: A study of elders in online travel communities

“…Authors have already mentioned the recent work by Gu [12] in which travel tips would be extracted from travel reviews. Other recent threads of research in this field are represented by Bhatnagar, who also proposed a framework for extracting more subtle, albeit more general and simpler aspects of travel experiences, and a study concerning a methodology of mapping the data related to medical tourism in South Korea done by [14].…”

Medical Data Stream Distribution Pattern Association Rule Mining Algorithm Based on Density Estimation

“…Generally, the mining of the distribution pattern association rule requires the following steps: First, collecting the original data, which often takes a long time; second, identifying the basic distribution conditions by establishing a data distribution histogram; third, conducting the parameter estimation to reflect the medical data distribution characteristics; fourth, performing the fitness test on the collected data [10], [11]. If the test results do not match the assumed distribution, return to the second step for reanalysis [12], [13]. Evidently, the traditional data distribution pattern association rule mining method has the deficiencies of large computation and cumbersome steps [14].…”