Can Big Data Forecast North Korean Military Aggression?

Young Han (Andy) Kim, Hyoung-Goo Kang, Jong Kyu Lee

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Can textual analysis improve statistical prediction of risky geopolitical events? North Korea is the greatest source of geopolitical risk for South Korea due to the former’s unpredictable and secretive military actions against the latter. We find that the tone of English language news articles published by non-South Korean news media, especially U.K. news media, has significant predictive power about North Korean military aggressions. The inclusion of language tone improves the predictive power of the empirical model by as much as 47%.

Original languageEnglish
Pages (from-to)666-683
Number of pages18
JournalDefence and Peace Economics
Volume29
Issue number6
DOIs
StatePublished - 2018 Sep 19

Fingerprint

aggression
news
Military
North Korea
South Korea
statistical analysis
English language
inclusion
event
language
Predictive power
News media
Aggression
News
Prediction
Empirical model
Inclusion
Language
Textual analysis

Keywords

  • Geopolitical risk
  • North Korea
  • big data
  • media
  • textual analysis

Cite this

Kim, Young Han (Andy) ; Kang, Hyoung-Goo ; Lee, Jong Kyu. / Can Big Data Forecast North Korean Military Aggression?. In: Defence and Peace Economics. 2018 ; Vol. 29, No. 6. pp. 666-683.
@article{1f3b62c49a754428a44a4b5d84094191,
title = "Can Big Data Forecast North Korean Military Aggression?",
abstract = "Can textual analysis improve statistical prediction of risky geopolitical events? North Korea is the greatest source of geopolitical risk for South Korea due to the former’s unpredictable and secretive military actions against the latter. We find that the tone of English language news articles published by non-South Korean news media, especially U.K. news media, has significant predictive power about North Korean military aggressions. The inclusion of language tone improves the predictive power of the empirical model by as much as 47{\%}.",
keywords = "Geopolitical risk, North Korea, big data, media, textual analysis",
author = "Kim, {Young Han (Andy)} and Hyoung-Goo Kang and Lee, {Jong Kyu}",
year = "2018",
month = "9",
day = "19",
doi = "10.1080/10242694.2016.1270736",
language = "English",
volume = "29",
pages = "666--683",
journal = "Defence and Peace Economics",
issn = "1024-2694",
number = "6",

}

Can Big Data Forecast North Korean Military Aggression? / Kim, Young Han (Andy); Kang, Hyoung-Goo; Lee, Jong Kyu.

In: Defence and Peace Economics, Vol. 29, No. 6, 19.09.2018, p. 666-683.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Can Big Data Forecast North Korean Military Aggression?

AU - Kim, Young Han (Andy)

AU - Kang, Hyoung-Goo

AU - Lee, Jong Kyu

PY - 2018/9/19

Y1 - 2018/9/19

N2 - Can textual analysis improve statistical prediction of risky geopolitical events? North Korea is the greatest source of geopolitical risk for South Korea due to the former’s unpredictable and secretive military actions against the latter. We find that the tone of English language news articles published by non-South Korean news media, especially U.K. news media, has significant predictive power about North Korean military aggressions. The inclusion of language tone improves the predictive power of the empirical model by as much as 47%.

AB - Can textual analysis improve statistical prediction of risky geopolitical events? North Korea is the greatest source of geopolitical risk for South Korea due to the former’s unpredictable and secretive military actions against the latter. We find that the tone of English language news articles published by non-South Korean news media, especially U.K. news media, has significant predictive power about North Korean military aggressions. The inclusion of language tone improves the predictive power of the empirical model by as much as 47%.

KW - Geopolitical risk

KW - North Korea

KW - big data

KW - media

KW - textual analysis

UR - http://www.scopus.com/inward/record.url?scp=85010669757&partnerID=8YFLogxK

U2 - 10.1080/10242694.2016.1270736

DO - 10.1080/10242694.2016.1270736

M3 - Article

AN - SCOPUS:85010669757

VL - 29

SP - 666

EP - 683

JO - Defence and Peace Economics

JF - Defence and Peace Economics

SN - 1024-2694

IS - 6

ER -