Construction of a News Classification System Related to Information Security Incidents

Jiansen Zhao, Hiroshi Takahashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this study, based on previous studies on the impact of news related to information security incidents on stock prices, we attempted to extract news related to information security incidents by using sentence similarity calculation in BERT. The stock price fluctuations of the sample news and the extracted news were also measured by event study and compared to verify the effectiveness of the classification model. As a result, the news data with a similarity of about 85% approximates the results of event studies in previous studies. The potential of the classification system was demonstrated.

Original languageEnglish
Title of host publicationAgents and Multi-Agent Systems
Subtitle of host publicationTechnologies and Applications 2022 - Proceedings of 16th KES International Conference, KES-AMSTA 2022
EditorsGordan Jezic, Yun-Heh Jessica Chen-Burger, Mario Kusek, Roman Šperka, Robert J. Howlett, Robert J. Howlett, Robert J. Howlett, Lakhmi C. Jain, Lakhmi C. Jain
PublisherSpringer Science and Business Media Deutschland GmbH
Pages125-133
Number of pages9
ISBN (Print)9789811933585
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event16th KES International Conference on Agents and Multi-Agent Systems: Technologies and Applications, KES-AMSTA 2022 - Rhodes, Greece
Duration: 2022 Jun 202022 Jun 22

Publication series

NameSmart Innovation, Systems and Technologies
Volume306
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference16th KES International Conference on Agents and Multi-Agent Systems: Technologies and Applications, KES-AMSTA 2022
Country/TerritoryGreece
CityRhodes
Period22/6/2022/6/22

Keywords

  • Information security incidents
  • Natural language processing

ASJC Scopus subject areas

  • Decision Sciences(all)
  • Computer Science(all)

Fingerprint

Dive into the research topics of 'Construction of a News Classification System Related to Information Security Incidents'. Together they form a unique fingerprint.

Cite this