search for




 

Analysis of reporting characteristics of newspapers in the 19th presidential election based on random forest
Journal of the Korean Data & Information Science Society 2018;29:367-75
Published online March 31, 2018
© 2018 Korean Data and Information Science Society.

HyunChae Jo1 · Cheolyong Park2

12Department of Statistics, Keimyung University
Correspondence to: Professor, Department of Statistics, Keimyung University, Daegu 42601, Korea. E-mail: cypark1@kmu.ac.kr
Received January 18, 2018; Revised February 19, 2018; Accepted March 5, 2018.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
People usually get information from mass media for their decision in direct election like presidential election. Especially each newspaper shows its disposition and tends to support specific party during the election. The 19th presidential election was very important and thus, in this study, we aimed to analyze reporting characteristics of newspapers for five major candidates in this election. More specifically, in this study, our analysis utilized the number of newspaper articles for some key words from 13 newspapers selected from BigKinds website. We calculated a proximity matrix between newspapers based on random forest, and then drew a two dimensional perceptual map of the matrix based on multidimensional scaling. From the map, we can interpret that the first axis represents the total number of newspaper articles and the second axis represents conservative vs non-conservative groups of newspapers.
Keywords : BigKinds website, multidimensional scaling, proximity matrix, random forest.