For the past two decades, North Korea has made a series of military provocations, destabilizing the regional security of East Asia. In particular, Pyongyang has launched several conventional attacks on South Korea. Although these attacks seem unpredictable and random, we attempt in this article to find some patterns in North Korean provocations. To this end, we employ a machine-learning technique to analyze news articles of the Korean Central News Agency (KCNA) from 1997 to 2013. Based on five key words (‘years,’ ‘signed,’ ‘assembly,’ ‘June,’ and ‘Japanese’), our model identifies North Korean provocations with 82% accuracy. Further investigation into these attack words and the contexts in which they appear produces significant insights into the ways in which we can detect North Korean provocations. International Relations of the Asia-Pacific Vol. 0 No. 0 # The Author 2016. Published by Oxford University Press in association with the Japan Association of International Relations; all rights reserved. For permissions, please email: journals.permissions@oup.com International Relations of the Asia-Pacific Volume 0, (2016) 1–28 doi: 10.1093/irap/lcw016 International Relations of the Asia-Pacific Advance Access published October 19, 2016 by gest on O cber 3, 2016 http://iraprdjournals.org/ D ow nladed from

中文翻译：

---

检测朝鲜军事挑衅的模式：机器学习告诉我们什么

过去二十年来，朝鲜进行了一系列军事挑衅，破坏了东亚地区的安全稳定。特别是，平壤对韩国发动了几次常规攻击。尽管这些攻击看似不可预测和随机，但我们试图在本文中找到朝鲜挑衅的一些模式。为此，我们采用机器学习技术来分析朝鲜中央通讯社 (KCNA) 从 1997 年到 2013 年的新闻文章。 基于五个关键词（“年”、“签名”、“集会”、“六月”， ' 和 'Japanese')，我们的模型以 82% 的准确率识别朝鲜的挑衅。对这些攻击词及其出现的上下文进行进一步调查，可以对我们检测朝鲜挑衅的方式产生重要的见解。亚太国际关系卷。0 No. 0 # 作者 2016. 牛津大学出版社与日本国际关系协会联合出版；版权所有。如需许可，请发送电子邮件至：journals.permissions@oup.com International Relations of the Asia-Pacific Volume 0, (2016) 1–28 doi: 10.1093/irap/lcw016 International Relations of the Asia-Pacific Advance Access 于 2016 年 10 月 19 日出版作者：2016 年 10 月 3 日 http://iraprdjournals.org/ 下载自