• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Financial Text Mining: Market Sentiment Analysis and Document Semantic Similarity for Different Languages

Research Project

Project/Area Number 18K11558
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 62020:Web informatics and service informatics-related
Research InstitutionKonan University

Principal Investigator

Seki Kazuhiro  甲南大学, 知能情報学部, 教授 (30444566)

Project Period (FY) 2018-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2021: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2020: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2019: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Keywords深層学習 / 機械学習 / 大規模言語モデル / 景況感指数 / 足元予測 / 多言語モデル / 文書間類似度 / センチメント分析 / 経済指標 / 時系列分析 / ナウキャスト / テキストアナリティクス / 感情分析 / ニューラルネットワーク / テキスト類似度 / 多言語機械翻訳 / データマイニング / 文書類似度 / 異言語情報検索 / テキストマイニング / 市場感情分析
Outline of Final Research Achievements

In this research, we studied (1) business sentiment forecast and (2) estimation of similarity between documents written in different languages, with the aim of promoting research on text mining in the financial and economic fields by utilizing a large amount of textual information such as news articles. For the former, we employed a model based on a self-attention mechanism, which has become the mainstream in recent natural language processing tasks, and achieved robust and highly accurate business sentiment prediction. For the latter, we successfully estimated the semantic document similarity between Japanese and English, and between English and Hindi, by using the internal representation of a translation model based on deep learning.

Academic Significance and Societal Importance of the Research Achievements

従来はアンケートなどのコスト・時間がかかる集計調査によっていた景況感が低コストかつほぼリアルタイムで行えることが示されたことにより,本研究成果を利用することで,金融当局の政策や企業の意思決定がよりタイムリーかつ効果的に行えるものと期待できる.さらに,異言語の文間の類似度を高精度で推定できることが明らかになったことから,これを発展させ前者と併用することで,言語の壁を超えて金融・経済関連テキストデータを統一的に分析することが可能となる.

Report

(6 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • 2018 Research-status Report
  • Research Products

    (12 results)

All 2022 2021 2020 2019 2018

All Journal Article (9 results) (of which Peer Reviewed: 9 results,  Open Access: 3 results) Presentation (3 results) (of which Int'l Joint Research: 1 results,  Invited: 1 results)

  • [Journal Article] Turning News Texts into Business Sentiment2022

    • Author(s)
      Kazuhiro Seki
    • Journal Title

      44th European Conference on Information Retrieval (ECIR 2022)

      Volume: - Pages: 311-315

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] News-based business sentiment and its properties as an economic index2022

    • Author(s)
      Kazuhiro Seki, Yusuke Ikuta, and Yoichi Matsubayashi
    • Journal Title

      Information Processing & Management

      Volume: 59 Issue: 2 Pages: 102795-102795

    • DOI

      10.1016/j.ipm.2021.102795

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Nowcasting Business Sentiment from Economic News Articles2021

    • Author(s)
      関和広,生田祐介
    • Journal Title

      情報処理学会論文誌

      Volume: 62 Issue: 5 Pages: 1288-1297

    • DOI

      10.20729/00211101

    • NAID

      170000184877

    • Year and Date
      2021-05-15
    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Cross-lingual text similarity exploiting neural machine translation models2021

    • Author(s)
      Kazuhiro Seki
    • Journal Title

      Journal of Information Science

      Volume: 47 Issue: 3 Pages: 404-418

    • DOI

      10.1177/0165551520912676

    • Related Report
      2021 Research-status Report 2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] 経済ニュースによる景況感指数の足元予測2021

    • Author(s)
      関和広, 生田祐介
    • Journal Title

      情報処理学会論文誌

      Volume: 5

    • NAID

      170000184877

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] S-APIR: News-Based Business Sentiment Index2020

    • Author(s)
      Kazuhiro Seki and Yusuke Ikuta
    • Journal Title

      Proceedings of 24th European Conference on Advances in Databases and Information Systems

      Volume: -

    • Related Report
      2019 Research-status Report
    • Peer Reviewed
  • [Journal Article] On Cross-Lingual Text Similarity Using Neural Translation Models2019

    • Author(s)
      Kazuhiro Seki
    • Journal Title

      Journal of Information Processing

      Volume: 27 Issue: 0 Pages: 315-321

    • DOI

      10.2197/ipsjjip.27.315

    • NAID

      130007611520

    • ISSN
      1882-6652
    • Related Report
      2018 Research-status Report
    • Peer Reviewed / Open Access
  • [Journal Article] Estimating Business Sentiment from News Texts2019

    • Author(s)
      Kazuhiro Seki and Yusuke Ikuta
    • Journal Title

      Proceedings of the 2nd IEEE Artificial Intelligence and Knowledge Engineering

      Volume: -

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Journal Article] Exploring Neural Translation Models for Cross-Lingual Text Similarity2018

    • Author(s)
      Kazuhiro Seki
    • Journal Title

      Proceedings of the 27th ACM International Conference on Information and Knowledge Management (CIKM)

      Volume: - Pages: 1591-1594

    • Related Report
      2018 Research-status Report
    • Peer Reviewed
  • [Presentation] テキストデータを利用した新しい景況感指標の開発と応用2022

    • Author(s)
      関和広,生田祐介,松林洋一
    • Organizer
      AI・ビッグデータ経済モデル研究会
    • Related Report
      2022 Annual Research Report
    • Invited
  • [Presentation] ニュース記事に基づく景気指標S-APIRの開発2020

    • Author(s)
      関和広, 生田祐介, 松林洋一
    • Organizer
      第24回人工知能学会金融情報学研究会
    • Related Report
      2019 Research-status Report
  • [Presentation] Estimating Business Sentiment from News Texts2019

    • Author(s)
      Kazuhiro Seki and Yusuke Ikuta
    • Organizer
      The 2nd IEEE Artificial Intelligence and Knowledge Engineering
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2018-04-23   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi