Construction of news article evaluation system using language generation model

Yoshihiro Nishi, Aiko Suge, Hiroshi Takahashi

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

Abstract

This study constructed a news article evaluation system that utilizes a language generation model to analyze financial markets. This system enables us to analyze the effect of news articles distributed in financial markets on the stock price of a company. We added the generated news articles as data for analysis through GPT-2 and verified the accuracy of the constructed system. As a result of empirical analyses, we confirmed that the accuracy of the model with the generated news articles improved. More detailed analyses are planned for the future.

Original languageEnglish
Title of host publicationAgents and Multi-Agent Systems
Subtitle of host publicationTechnologies and Applications - 14th KES International Conference, KES-AMSTA 2020, Proceedings
EditorsG. Jezic, M. Kusek, J. Chen-Burger, R. Sperka, Robert J. Howlett, Robert J. Howlett, Lakhmi C. Jain, Lakhmi C. Jain, Lakhmi C. Jain
PublisherSpringer
Pages313-320
Number of pages8
ISBN (Print)9789811557637
DOIs
Publication statusPublished - 2020 Jan 1
Event14th International KES Conference on Agents and Multi-Agent Systems: Technologies and Applications, KES-AMSTA 2020 - Split, Croatia
Duration: 2020 Jun 172020 Jul 19

Publication series

NameSmart Innovation, Systems and Technologies
Volume186
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference14th International KES Conference on Agents and Multi-Agent Systems: Technologies and Applications, KES-AMSTA 2020
CountryCroatia
CitySplit
Period20/6/1720/7/19

Keywords

  • Deep learning
  • Financial markets
  • GPT-2
  • Language generation
  • LSTM
  • Natural language processing
  • News evaluation system

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Construction of news article evaluation system using language generation model'. Together they form a unique fingerprint.

Cite this