Extraction of Major Structural Elements for Successful Aging in Korea through Social Big Data Analysis
SeoYoun Hong
SeoYoun Hong, Soonchunhyang University South, Korea.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 2758-2762 | Volume-8 Issue-7, May 2019 | Retrieval Number: G6396058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This study aimed to extract key words which can predict ‘health-related quality of life’ and ‘successful aging’ among the Korean old people using social big data and rank those key words in accuracy (Mean Decrease Accuracy (%IncMSE)) and importance (Mean Decrease Gini (IncNodePurity)) in predicting dependent variables. To analyze the data, this study applied Random Forest analysis in R-3.5.0 Version Program. It was found that the relative importance levels (Mean Decrease Gini (IncNodePurity)) of variables were as follows: hobby, preparation, education, sports, volunteer service, love, exercise, welfare, job, and medical care, etc. and, in accuracy levels in predicting successful aging (Mean Decrease Accuracy (%IncMSE)), the rank order of variables were as follows: hobby, love, recognition, sports, welfare, exercise, education, pension, depression, and medical care, etc. In particular, ‘hobby’ activities of old people showed higher importance and accuracy than those of other word, proving that it is an important variable to predict successful aging among Korean old people.
Keyword: Successful Aging, Social Big Data, Random Forest Analysis.
Scope of the Article: Big Data Analytics