Open AccessExploring Subjective Well-Being Factors with Support Vector Machine
Author(s) -
Du Ni,
Ming K. Lim,
Zhi Cai Xiao,
Xiaodong Feng
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.36.29100
Subject(s) - happiness , generosity , affect (linguistics) , support vector machine , life expectancy , per capita , language change , psychology , linear regression , social support , sample (material) , econometrics , social psychology , economics , demography , statistics , computer science , political science , artificial intelligence , mathematics , sociology , population , art , chemistry , literature , communication , chromatography , law
National-level Subjective well-being (SWB) is known to be associated with six traditional factors, that is, GDP per capita, social support, healthy life expectancy, social freedom, generosity, and absence of corruption, but debates persist about the variability of these six factors. Whether the predicting in SWB is based only on these six factors or not? Are there any country-specific factors? Thus, we examined these two questions with the data sets from World Happiness Report and OECD database for U.S.. By control-ling the other factors except only one, we employed Support Vector Machine (SVM) to identify the weight of each factor without worrying about the limitations caused by the small size of the sample in years. We found that another three factors (protein con-sumption, fruit consumption and physician ratio among all employee) in addition to the six traditional factors can also affect na-tional-level SWB in U.S.; Moreover, the power of SVW in prediction is as high as 95.08%, which is much greater than that present-ed by the linear regression models (74.3%).